title stringlengths 1 300 | score int64 0 8.54k | selftext stringlengths 0 41.5k | created timestamp[ns]date 2023-04-01 04:30:41 2026-03-04 02:14:14 ⌀ | url stringlengths 0 878 | author stringlengths 3 20 | domain stringlengths 0 82 | edited timestamp[ns]date 1970-01-01 00:00:00 2026-02-19 14:51:53 | gilded int64 0 2 | gildings stringclasses 7
values | id stringlengths 7 7 | locked bool 2
classes | media stringlengths 646 1.8k ⌀ | name stringlengths 10 10 | permalink stringlengths 33 82 | spoiler bool 2
classes | stickied bool 2
classes | thumbnail stringlengths 4 213 ⌀ | ups int64 0 8.54k | preview stringlengths 301 5.01k ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
PLX/PEX PCIe 4.0 seems to help for LLMs and P2P! I.e. PEX88096 (1 PCIe 4.0 X16 to 5 PCIE 4.0 X16) and others, and comparison vs bifurcation. | 39 | Hello guys, hoping you're having a good day.
I do this post if it helps for information for some users that don't know about switches.
Before anything, I have all the switches I mention on this post but the PCIe 5.0 ones and PEX88080 one. All bought from aliexpress, and all working fine, ranging from 100 to 500USD. I... | 2025-12-22T14:01:51 | https://www.reddit.com/r/LocalLLaMA/comments/1pt0av6/plxpex_pcie_40_seems_to_help_for_llms_and_p2p_ie/ | panchovix | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pt0av6 | false | null | t3_1pt0av6 | /r/LocalLLaMA/comments/1pt0av6/plxpex_pcie_40_seems_to_help_for_llms_and_p2p_ie/ | false | false | 39 | null | |
Why does this feel more stable than a normal LLM chat? | 1 | [removed] | 2025-12-22T13:57:32 | QualityEvery6965 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1pt075k | false | null | t3_1pt075k | /r/LocalLLaMA/comments/1pt075k/why_does_this_feel_more_stable_than_a_normal_llm/ | false | false | default | 1 | {'enabled': True, 'images': [{'id': 'jh1tc3tbhr8g1', 'resolutions': [{'height': 134, 'url': 'https://preview.redd.it/jh1tc3tbhr8g1.jpeg?width=108&crop=smart&auto=webp&s=a7b1211520ca4b39d8169b810299893f354204e1', 'width': 108}, {'height': 268, 'url': 'https://preview.redd.it/jh1tc3tbhr8g1.jpeg?width=216&crop=smart&auto=... | |
Agent builders/devs. What are the most frustrating unsolved problems you experience when building agents ? | 0 | Let me hear your thoughts guys I’m all ears 👂
I’ve been talking a lot lately to agent developers because I’ve been building with some langchain users a tool called Scope (link in the comments ).
And we’re struggling to understand if the issue we wish to resolve, which in one sentence is :
“help agent developers qu... | 2025-12-22T13:57:07 | https://www.reddit.com/r/LocalLLaMA/comments/1pt06tv/agent_buildersdevs_what_are_the_most_frustrating/ | AdVivid5763 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pt06tv | false | null | t3_1pt06tv | /r/LocalLLaMA/comments/1pt06tv/agent_buildersdevs_what_are_the_most_frustrating/ | false | false | self | 0 | null |
[Tool] imesde: Zero-GPU, In-Memory Vector Engine for Real-Time Local RAG | 6 | Hi r/LocalLLaMA,
I wanted to share a project I’ve been working on called `imesde` (In-MEmory Streaming Data Engine).
If you’ve ever tried to build a RAG system for live data streams (logs, tweets, stock tickers, or even a fast Twitch chat), you’ve probably hit the "Knowledge Gap": traditional Vector DBs are great for... | 2025-12-22T13:44:33 | https://www.reddit.com/r/LocalLLaMA/comments/1pszwoq/tool_imesde_zerogpu_inmemory_vector_engine_for/ | alessiopelliccione | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pszwoq | false | null | t3_1pszwoq | /r/LocalLLaMA/comments/1pszwoq/tool_imesde_zerogpu_inmemory_vector_engine_for/ | false | false | self | 6 | {'enabled': False, 'images': [{'id': 'uKpKFUAZri4LO9ESYSMUGQVgnfXaA_xzIVPLFs4vg5g', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/uKpKFUAZri4LO9ESYSMUGQVgnfXaA_xzIVPLFs4vg5g.png?width=108&crop=smart&auto=webp&s=24cf33d6e0540ee7d27b0f6eeaab365a76fd1779', 'width': 108}, {'height': 108, 'url': 'h... |
using gemma for perception and normalization in agents? | 2 | If we use gemma 314B or 27B as a pre processor to responses received from tools, clean it as needed and feed only necessary info into the core llm for long agentic workflows and jobs, would we have much high accuracy and reliability? Are people using gemma in agents? | 2025-12-22T13:40:39 | https://www.reddit.com/r/LocalLLaMA/comments/1psztmt/using_gemma_for_perception_and_normalization_in/ | LankyLychee8916 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psztmt | false | null | t3_1psztmt | /r/LocalLLaMA/comments/1psztmt/using_gemma_for_perception_and_normalization_in/ | false | false | self | 2 | null |
72Gb VRAM (3x 3090) / 128Gb DDR4 / Mylan CPU What code model can I test? | 0 | Hey guys, just landed into the world of LocalLLM,
My rigs is small compare to some (planning on going up to 8x 3090 Q1 2026) however I'd like to test the capability on the 3x 3090, what model / setup have you run that for code specific?
I want to test this with Roocode and the bomerang feature - the goal would be t... | 2025-12-22T13:39:19 | https://www.reddit.com/r/LocalLLaMA/comments/1pszsn1/72gb_vram_3x_3090_128gb_ddr4_mylan_cpu_what_code/ | shvz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pszsn1 | false | null | t3_1pszsn1 | /r/LocalLLaMA/comments/1pszsn1/72gb_vram_3x_3090_128gb_ddr4_mylan_cpu_what_code/ | false | false | self | 0 | null |
Tracking LLM Benchmarks Across arXiv | 1 | alphaXiv indexed results from millions of papers to surface which models are SOTA according to open source research.
[https://www.alphaxiv.org/state-of-the-art](https://www.alphaxiv.org/state-of-the-art) | 2025-12-22T13:39:03 | https://v.redd.it/5mug8gaedr8g1 | Dear-Success-1441 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1pszsgd | false | {'reddit_video': {'bitrate_kbps': 2400, 'dash_url': 'https://v.redd.it/5mug8gaedr8g1/DASHPlaylist.mpd?a=1769002760%2CYTdmOTVmZDRiMjdlODBlMmFkZDBhMzhiOGIzZThjZjZiY2JhNjM2MzQ5YmFiZWI2Y2MwZDMxYzMzNGE3ZWM0Yw%3D%3D&v=1&f=sd', 'duration': 17, 'fallback_url': 'https://v.redd.it/5mug8gaedr8g1/CMAF_720.mp4?source=fallback', 'ha... | t3_1pszsgd | /r/LocalLLaMA/comments/1pszsgd/tracking_llm_benchmarks_across_arxiv/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'MDBsajBvYWVkcjhnMS29ePEkxjn8ArZXOta0FrRD7gYg5O_CjmkWTyFY5DID', 'resolutions': [{'height': 59, 'url': 'https://external-preview.redd.it/MDBsajBvYWVkcjhnMS29ePEkxjn8ArZXOta0FrRD7gYg5O_CjmkWTyFY5DID.png?width=108&crop=smart&format=pjpg&auto=webp&s=f18b67735df3b516b4939055db81c8aecc0c2... | |
Upgrade in 2026 or wait until the price of a new >1000GB/s 768GB VRAM/URAM machine is <=$4k? | 0 | Judging the state of the VRAM and Mac market, we would need to wait another 5-9 years to get a brand new >1000GB/s 768GB VRAM/URAM machine for less than 4k. Maybe it will be even worse, in 5-9years, so many people will have lost their jobs and the enterprise market will have become so profitable and big, that GPU ... | 2025-12-22T13:28:00 | https://www.reddit.com/r/LocalLLaMA/comments/1pszk1l/upgrade_in_2026_or_wait_until_the_price_of_a_new/ | power97992 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pszk1l | false | null | t3_1pszk1l | /r/LocalLLaMA/comments/1pszk1l/upgrade_in_2026_or_wait_until_the_price_of_a_new/ | false | false | self | 0 | null |
Looking for a stop motion / frame sequencing workflow for Wan 2.2? | 2 | Will you require a specific lora or a just settings variance/nodes to produce a stop motion 8 frame per second videos? Or a frame sequencing set up?
If not, can you make them via Z-image, Qwen edits...?
Thanks. | 2025-12-22T13:26:04 | https://www.reddit.com/r/LocalLLaMA/comments/1pszimg/looking_for_a_stop_motion_frame_sequencing/ | Slight_Tone_2188 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pszimg | false | null | t3_1pszimg | /r/LocalLLaMA/comments/1pszimg/looking_for_a_stop_motion_frame_sequencing/ | false | false | self | 2 | null |
Building a Local LLM for Homeschooling on an Old i5-3570—Any Advice? | 2 | I’m a homeschooling parent, and—purely out of curiosity and privacy concerns—I’m trying to run a local LLM on my aging desktop: an Intel i5-3570 with 16GB RAM. Yeah, I know it sounds ridiculous in 2025, but I really don’t want to send my kids’ learning profiles or personal data to any public/cloud API.
My goal is to b... | 2025-12-22T13:17:17 | https://www.reddit.com/r/LocalLLaMA/comments/1pszbz6/building_a_local_llm_for_homeschooling_on_an_old/ | ManufacturerLive6214 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pszbz6 | false | null | t3_1pszbz6 | /r/LocalLLaMA/comments/1pszbz6/building_a_local_llm_for_homeschooling_on_an_old/ | false | false | self | 2 | null |
Devstral 2 vs Devstral Small 2: A 30-Minute Playground Test for Multi-File Coding Tasks | 1 | [removed] | 2025-12-22T13:06:28 | https://www.reddit.com/r/LocalLLaMA/comments/1psz44k/devstral_2_vs_devstral_small_2_a_30minute/ | Unique_Can_2569 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psz44k | false | null | t3_1psz44k | /r/LocalLLaMA/comments/1psz44k/devstral_2_vs_devstral_small_2_a_30minute/ | false | false | self | 1 | null |
Kimi K2 Thinking is the least sycophantic open-source AI, according to research by Anthropic | 75 | 2025-12-22T12:58:00 | https://www.reddit.com/r/LocalLLaMA/comments/1psyxwo/kimi_k2_thinking_is_the_least_sycophantic/ | InternationalAsk1490 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psyxwo | false | null | t3_1psyxwo | /r/LocalLLaMA/comments/1psyxwo/kimi_k2_thinking_is_the_least_sycophantic/ | false | false | 75 | null | ||
upstage/Solar-Open-100B · Hugging Face | 115 | ...do you remember [https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0) from 2024?
It looks like they have something new:
# [](https://huggingface.co/upstage/Solar-Open-100B#solar-open)Solar Open
**Solar Open** is Upstage's flagship **102B-parameter** l... | 2025-12-22T12:47:16 | https://huggingface.co/upstage/Solar-Open-100B | jacek2023 | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1psyqha | false | null | t3_1psyqha | /r/LocalLLaMA/comments/1psyqha/upstagesolaropen100b_hugging_face/ | false | false | default | 115 | {'enabled': False, 'images': [{'id': 'KGZNZzWd5K6vM05pplkzhPrPxHhbMAP1w-s6MnLTkhM', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/KGZNZzWd5K6vM05pplkzhPrPxHhbMAP1w-s6MnLTkhM.png?width=108&crop=smart&auto=webp&s=9bb4811c12a9d4a0051defb855ee79a97b25f439', 'width': 108}, {'height': 116, 'url': 'h... |
Built a small client-side LLM preprocessor to reduce API token costs — looking for honest feedback | 1 | [removed] | 2025-12-22T12:45:34 | https://www.reddit.com/r/LocalLLaMA/comments/1psypb7/built_a_small_clientside_llm_preprocessor_to/ | Admirable-Degree2876 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psypb7 | false | null | t3_1psypb7 | /r/LocalLLaMA/comments/1psypb7/built_a_small_clientside_llm_preprocessor_to/ | false | false | self | 1 | null |
Best model choice | 2 | Hi all. I’m looking for advice on what model is best for my project:
Custom RAG protocol to summarise regulatory requirement held across various government laws/regs/guidance.
I’m only working with 8GB of VRAM at the moment and 32GB of RAM but ideally I’d like to avoid offloading to manage latency.
Context window is... | 2025-12-22T12:45:19 | https://www.reddit.com/r/LocalLLaMA/comments/1psyp5n/best_model_choice/ | Dank-but-true | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psyp5n | false | null | t3_1psyp5n | /r/LocalLLaMA/comments/1psyp5n/best_model_choice/ | false | false | self | 2 | null |
Same LLMs, fewer prompts — why does this feel more reliable? | 0 | Most AI chats today rely on:
• prompt-based personality
• implicit assumptions
• probabilistic drift over time
I tried the opposite approach:
• architecture-defined behavior
• explicit state and routing
• treating the LLM as a renderer, not a decision-maker
Unexpectedly, the system became more logical and... | 2025-12-22T12:35:01 | QualityEvery6965 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1psyi5o | false | null | t3_1psyi5o | /r/LocalLLaMA/comments/1psyi5o/same_llms_fewer_prompts_why_does_this_feel_more/ | false | false | default | 0 | {'enabled': True, 'images': [{'id': '9rejj1se2r8g1', 'resolutions': [{'height': 134, 'url': 'https://preview.redd.it/9rejj1se2r8g1.jpeg?width=108&crop=smart&auto=webp&s=50f9a047547925e99c9a90236dc9ca1d9f5d03b3', 'width': 108}, {'height': 268, 'url': 'https://preview.redd.it/9rejj1se2r8g1.jpeg?width=216&crop=smart&auto=... | |
[User research] Building a long-running single/multi-agent system — what real workflows should it handle? (free credits) | 0 | Hey all — disclosure: I’m one of the builders of an **agent system** that supports **long-running tasks** (multi-day / stateful) and **single or multi-agent workflows**.
I’m running a **use-case collection** to pressure-test what people actually want and where existing agents fail.
**What I’m looking for:**
* A work... | 2025-12-22T12:31:50 | https://www.reddit.com/r/LocalLLaMA/comments/1psyg1s/user_research_building_a_longrunning/ | PerceptionAble5423 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psyg1s | false | null | t3_1psyg1s | /r/LocalLLaMA/comments/1psyg1s/user_research_building_a_longrunning/ | false | false | self | 0 | null |
Built a safe and simple way to connect agents to your data stack | 0 | Here’s how Pylar works in simple terms.
First, you connect Pylar to where your data already lives, using pre-built integrations to databases, warehouses, CRMs, product and support tools. No rebuilding, no moving data around.
Next, you create **agent data views**. Think of these as clean, task-specific snapshots of yo... | 2025-12-22T12:12:46 | https://v.redd.it/shus72ijyq8g1 | Better-Department662 | /r/LocalLLaMA/comments/1psy3at/built_a_safe_and_simple_way_to_connect_agents_to/ | 1970-01-01T00:00:00 | 0 | {} | 1psy3at | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/shus72ijyq8g1/DASHPlaylist.mpd?a=1769127174%2CODU2YTRjMjQ2ZDdhZTlkMmNmZWJhM2JjNjI0Nzc2Y2Q4YWMzYzZjOTdlMGZjY2E5MTUzYjcxYjA3MWI2ZDIwMA%3D%3D&v=1&f=sd', 'duration': 105, 'fallback_url': 'https://v.redd.it/shus72ijyq8g1/CMAF_1080.mp4?source=fallback', '... | t3_1psy3at | /r/LocalLLaMA/comments/1psy3at/built_a_safe_and_simple_way_to_connect_agents_to/ | false | false | 0 | {'enabled': False, 'images': [{'id': 'enFjMXJhbGp5cThnMWRa4OkQHDhkf_86kr5Q8OcB2_phR992cHwluPjyGLdU', 'resolutions': [{'height': 67, 'url': 'https://external-preview.redd.it/enFjMXJhbGp5cThnMWRa4OkQHDhkf_86kr5Q8OcB2_phR992cHwluPjyGLdU.png?width=108&crop=smart&format=pjpg&auto=webp&s=e390b0ba7417e1560174758acb2c18b738cc7... | |
Qwen3-235B-W4A16 is S tier | 19 | The best model I’ve tried that can fit on my 200GB VRAM is surprisingly this Qwen model.
It is able to navigate complex puzzles, and agentic environments with grace, it’s a good coder, and extremely fast.
I am even comparing this to remotely hosted FP16 models like GLM-4.6
This might be old news but I wrote of Qwen... | 2025-12-22T12:12:42 | https://www.reddit.com/r/LocalLLaMA/comments/1psy387/qwen3235bw4a16_is_s_tier/ | Sero_x | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psy387 | false | null | t3_1psy387 | /r/LocalLLaMA/comments/1psy387/qwen3235bw4a16_is_s_tier/ | false | false | self | 19 | null |
Local RAG with small models with hallucination mitigation | 35 | Hi all,
I started this as a personal project, aiming to build something fully customizable and suitable to my needs, allowing me to study technical documentation, books and scientific articles locally, privately - therefore allowing me to include larger contexts on proprietary docs within my work. However, I was genui... | 2025-12-22T12:08:03 | https://v.redd.it/cvrl5akkwq8g1 | ljubobratovicrelja | /r/LocalLLaMA/comments/1psy0ag/local_rag_with_small_models_with_hallucination/ | 1970-01-01T00:00:00 | 0 | {} | 1psy0ag | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/cvrl5akkwq8g1/DASHPlaylist.mpd?a=1769126896%2CN2ZmMjRmNmU3NjcxYjIxNTQ0NjM5YjI2ODA1NGFmZjJhOWQzMmE1YzliYzFkNTI4NjUyODQ1NjNmODI5ODA5YQ%3D%3D&v=1&f=sd', 'duration': 176, 'fallback_url': 'https://v.redd.it/cvrl5akkwq8g1/CMAF_1080.mp4?source=fallback', '... | t3_1psy0ag | /r/LocalLLaMA/comments/1psy0ag/local_rag_with_small_models_with_hallucination/ | false | false | 35 | {'enabled': False, 'images': [{'id': 'YTFtcnJ1a2t3cThnMS9Ei5brJy4BdsT9diAS7Z-bKUm9Q2FZKYFGqvrqb-vS', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/YTFtcnJ1a2t3cThnMS9Ei5brJy4BdsT9diAS7Z-bKUm9Q2FZKYFGqvrqb-vS.png?width=108&crop=smart&format=pjpg&auto=webp&s=730319e25a830a4f7e5a83ea3b5710e7d03e0... | |
Will the RAM shortage cause hike in hosting and compute costs? | 2 | I know this is not related to the LocalLLaMA type posts but kinda linked to the AI world? Will normal compute costs, shared servers, vps costs go up in the next few years due to this RAM and storage shortages?
Any insight is appreciated. Thanks | 2025-12-22T12:04:14 | https://www.reddit.com/r/LocalLLaMA/comments/1psxxss/will_the_ram_shortage_cause_hike_in_hosting_and/ | salary_pending | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psxxss | false | null | t3_1psxxss | /r/LocalLLaMA/comments/1psxxss/will_the_ram_shortage_cause_hike_in_hosting_and/ | false | false | self | 2 | null |
GLM 4.7 Frontend tests (Source: Chinese Forum） | 24 | 2025-12-22T11:54:28 | https://www.reddit.com/r/LocalLLaMA/comments/1psxr5j/glm_47_frontend_tests_source_chinese_forum/ | External_Mood4719 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psxr5j | false | null | t3_1psxr5j | /r/LocalLLaMA/comments/1psxr5j/glm_47_frontend_tests_source_chinese_forum/ | false | false | 24 | null | ||
I made ai play games | 0 | i made them play games like mafia and a style hunt game. i only have 2 of the match
THIS IS AN EXPERIMENT NOT A VERDICT
tho this game is not currently optimized and fair
so far the best pure reasoning is claude, rarely makes error, spots inconsistensy best manipulator is GPT, gpt controls without commanding, uses a... | 2025-12-22T11:53:36 | https://www.reddit.com/r/LocalLLaMA/comments/1psxqle/i_made_ai_play_games/ | WindowKind4905 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psxqle | false | null | t3_1psxqle | /r/LocalLLaMA/comments/1psxqle/i_made_ai_play_games/ | false | false | self | 0 | null |
Why does an LLM behave more logically when it’s not the system itself? | 1 | [removed] | 2025-12-22T11:45:52 | Aleksandr_Nikolaev | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1psxlsl | false | null | t3_1psxlsl | /r/LocalLLaMA/comments/1psxlsl/why_does_an_llm_behave_more_logically_when_its/ | false | false | default | 1 | {'enabled': True, 'images': [{'id': 'zq2fab5utq8g1', 'resolutions': [{'height': 134, 'url': 'https://preview.redd.it/zq2fab5utq8g1.jpeg?width=108&crop=smart&auto=webp&s=70914fc6f540a044966876f64b6c79c2f7c8d099', 'width': 108}, {'height': 268, 'url': 'https://preview.redd.it/zq2fab5utq8g1.jpeg?width=216&crop=smart&auto=... | |
Live Streaming Agent Framework development from scratch in go | 4 | Hey folks!
I’ve been documenting my personal learning journey on agent development and recently started weekly live streams on YouTube (every Sunday, 9–10pm SGT). If you're curious about how agent frameworks are built behind the scenes, feel free to follow along!
More context on why I’m doing this:
[https://a... | 2025-12-22T11:44:50 | https://www.reddit.com/r/LocalLLaMA/comments/1psxl51/live_streaming_agent_framework_development_from/ | praveensanap | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psxl51 | false | null | t3_1psxl51 | /r/LocalLLaMA/comments/1psxl51/live_streaming_agent_framework_development_from/ | false | false | self | 4 | null |
Spent weekend tuning LLM server to hone my nerdism so you don't have to. | 17 | The Art:
https://preview.redd.it/1rdwk3yykq8g1.jpg?width=2494&format=pjpg&auto=webp&s=562c0dcecf89a3227a2627572e902afca5384bfb
Tl;dr; I've spent some time setting up local AI server with various models for chat and agentic coding in VS code + Cline. The goal was to replace Ollama with llama.cpp and squeeze as much ... | 2025-12-22T11:07:28 | https://www.reddit.com/r/LocalLLaMA/comments/1pswyjm/spent_weekend_tuning_llm_server_to_hone_my/ | ChopSticksPlease | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pswyjm | false | null | t3_1pswyjm | /r/LocalLLaMA/comments/1pswyjm/spent_weekend_tuning_llm_server_to_hone_my/ | false | false | 17 | null | |
What's the point of hosting open source LLM on cloud? | 2 | I get Ollama is super popular to serve as a local driver for open source LLMs. On the other hand, do people actually self host on cloud? It sounds like a sensible idea for companies care about security. | 2025-12-22T10:56:04 | https://www.reddit.com/r/LocalLLaMA/comments/1pswrsw/whats_the_point_of_hosting_open_source_llm_on/ | Yersyas | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pswrsw | false | null | t3_1pswrsw | /r/LocalLLaMA/comments/1pswrsw/whats_the_point_of_hosting_open_source_llm_on/ | false | false | self | 2 | null |
M2.1 and M2 The difference? Hello? | 0 | 2025-12-22T10:40:22 | https://www.reddit.com/r/LocalLLaMA/comments/1pswj0n/m21_and_m2_the_difference_hello/ | Carinaaaatian | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pswj0n | false | null | t3_1pswj0n | /r/LocalLLaMA/comments/1pswj0n/m21_and_m2_the_difference_hello/ | false | false | 0 | null | ||
96 GB RAM: Intel Core Ultra 9 + NVIDIA or AMD Ryzen 9 ? | 3 | I'm shopping for my professional laptop where I need to experiment with local LLMs. It won't be a beast (it has to be my daily laptop) but I plan to learn on it and use that experience to later build a more powerful (non-laptop) system for my work team.
I am leaning towards a Thinkpad P14s G6 which exists in Intel or ... | 2025-12-22T10:33:34 | https://www.reddit.com/r/LocalLLaMA/comments/1pswf8s/96_gb_ram_intel_core_ultra_9_nvidia_or_amd_ryzen_9/ | cosmoschtroumpf | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pswf8s | false | null | t3_1pswf8s | /r/LocalLLaMA/comments/1pswf8s/96_gb_ram_intel_core_ultra_9_nvidia_or_amd_ryzen_9/ | false | false | self | 3 | null |
Jan-v2-VL-Max: A 30B multimodal model outperforming Gemini 2.5 Pro and DeepSeek R1 on execution-focused benchmarks | 126 | Hi, this is Bach from the Jan team.
We’re releasing Jan-v2-VL-max, a 30B multimodal model built for long-horizon execution.
Jan-v2-VL-max outperforms DeepSeek R1 and Gemini 2.5 Pro on the Illusion of Diminishing Returns benchmark, which measures execution length.
Built on Qwen3-VL-30B-A3B-Thinking, Jan-v2-VL-max sca... | 2025-12-22T10:21:02 | https://v.redd.it/80qbna7heq8g1 | Delicious_Focus3465 | /r/LocalLLaMA/comments/1psw818/janv2vlmax_a_30b_multimodal_model_outperforming/ | 1970-01-01T00:00:00 | 0 | {} | 1psw818 | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/80qbna7heq8g1/DASHPlaylist.mpd?a=1769120469%2CMTQ1OGI2NDk4ODk3Njc5ODc0YzBmNzYyYjcxMTM5NDM1YmFjMTdmYWVlNWQyYjA1ODJjNjIxNjk1ZmZmZGVlNw%3D%3D&v=1&f=sd', 'duration': 129, 'fallback_url': 'https://v.redd.it/80qbna7heq8g1/CMAF_1080.mp4?source=fallback', '... | t3_1psw818 | /r/LocalLLaMA/comments/1psw818/janv2vlmax_a_30b_multimodal_model_outperforming/ | false | false | 126 | {'enabled': False, 'images': [{'id': 'aTgxeDFoN2hlcThnMS3fkoPAQ79Dr1Rhop5Txa3dHZ8j7rKJLXSjpsKe44ta', 'resolutions': [{'height': 74, 'url': 'https://external-preview.redd.it/aTgxeDFoN2hlcThnMS3fkoPAQ79Dr1Rhop5Txa3dHZ8j7rKJLXSjpsKe44ta.png?width=108&crop=smart&format=pjpg&auto=webp&s=afbebbaf909a4ebbcd44ec278290c888fa000... | |
Chroma DB's weak Open Source commitment | 11 | Chroma's sparse vector search feature (and hybrid search) are only available on Chroma Cloud. This fact is "sparsly" documented and in direct violation of [their stated open source committments](https://docs.trychroma.com/cloud/getting-started):
>Under the hood, it's the exact same Apache 2.0–licensed Chroma—no forks,... | 2025-12-22T10:12:38 | https://www.reddit.com/r/LocalLLaMA/comments/1psw3ae/chroma_dbs_weak_open_source_commitment/ | Primary-Lake7507 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psw3ae | false | null | t3_1psw3ae | /r/LocalLLaMA/comments/1psw3ae/chroma_dbs_weak_open_source_commitment/ | false | false | self | 11 | {'enabled': False, 'images': [{'id': 'VuuczP9HNoYTov-eB4WwbkDAIIuDrCCVCLsfVnm3TAY', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/VuuczP9HNoYTov-eB4WwbkDAIIuDrCCVCLsfVnm3TAY.png?width=108&crop=smart&auto=webp&s=35e899638a374b00d5712e686a991bd1dbbe27e0', 'width': 108}, {'height': 113, 'url': 'h... |
i made a chatbot app | 0 | pc specs
\-ryzen 5 3600
\-8gb ram (not sure what ddr)
\-gt710
LLMs i downloaded
\-gemma 3:4b
\-Llama3.1
i used ollama as my server.
i used tkinter in python code with AI coding help. :)
took me a week since this is my first time | 2025-12-22T10:01:30 | https://v.redd.it/cvnlot5haq8g1 | Ok-Percentage1125 | /r/LocalLLaMA/comments/1psvwse/i_made_a_chatbot_app/ | 1970-01-01T00:00:00 | 0 | {} | 1psvwse | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/cvnlot5haq8g1/DASHPlaylist.mpd?a=1769119299%2COWNjZGQxNmJhOGYyZDEzNDFhMmUzNmMyY2ZlMjA0MTE4ZmMwZjg4ZTI3Mjc3YWZmYmM4NTg1YWI1ZjczNzAyMg%3D%3D&v=1&f=sd', 'duration': 93, 'fallback_url': 'https://v.redd.it/cvnlot5haq8g1/CMAF_1080.mp4?source=fallback', 'h... | t3_1psvwse | /r/LocalLLaMA/comments/1psvwse/i_made_a_chatbot_app/ | false | false | 0 | {'enabled': False, 'images': [{'id': 'eW03bWVtNmhhcThnMbpoeBY5AA1AiIW6vrBujrMDWn98cJdB7WdTp3_5UBEU', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/eW03bWVtNmhhcThnMbpoeBY5AA1AiIW6vrBujrMDWn98cJdB7WdTp3_5UBEU.png?width=108&crop=smart&format=pjpg&auto=webp&s=0f118b25e7125d900ab3e473000c08f4726c1... | |
Full-stack AI template v0.1.6 – now with OpenRouter support (great for routing to local models) + CLI enhancements | 1 | Hey r/LocalLLaMA,
Quick intro: This is an open-source generator for full-stack LLM apps (**FastAPI** backend + optional **Next.js** frontend). It supports **PydanticAI** and **LangChain** agents with streaming, persistence, and tools – and is easy to extend for local models.
Repo: [https://github.com/vstorm-co/full-s... | 2025-12-22T09:37:02 | https://github.com/vstorm-co/full-stack-fastapi-nextjs-llm-template | VanillaOk4593 | github.com | 1970-01-01T00:00:00 | 0 | {} | 1psvj9o | false | null | t3_1psvj9o | /r/LocalLLaMA/comments/1psvj9o/fullstack_ai_template_v016_now_with_openrouter/ | false | false | default | 1 | {'enabled': False, 'images': [{'id': 'IcFXco8uq4Vt6QCHYrbdWm_khgg7ohS0XFKt9YSOiWQ', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/IcFXco8uq4Vt6QCHYrbdWm_khgg7ohS0XFKt9YSOiWQ.png?width=108&crop=smart&auto=webp&s=273bc1b0317d299850e57083eccc86a1f6f28910', 'width': 108}, {'height': 108, 'url': 'h... |
I built a 100% Java RAG engine from scratch that runs on <500MB RAM | 5 | Hi folks,
I’ve spent the last few weeks building **LiteRAG**, a lightweight search & retrieval engine designed specifically for low-resource edge devices where running a full Python stack (LangChain + Chroma/FAISS + Torch) is too heavy.
It has a r**ecall@10 of \~75%**, this is without vector embeddings or any local t... | 2025-12-22T09:31:01 | https://www.reddit.com/r/LocalLLaMA/comments/1psvg25/i_built_a_100_java_rag_engine_from_scratch_that/ | Swimming-Regret-7278 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psvg25 | false | null | t3_1psvg25 | /r/LocalLLaMA/comments/1psvg25/i_built_a_100_java_rag_engine_from_scratch_that/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': 'tR9Qf4jYgiFNH1HF1IjIVK7pQZOIKOrHCrM2nRbS2_c', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/tR9Qf4jYgiFNH1HF1IjIVK7pQZOIKOrHCrM2nRbS2_c.png?width=108&crop=smart&auto=webp&s=bdafa992bf6bc4346a72a2a978b521e1ed12c8bf', 'width': 108}, {'height': 108, 'url': 'h... |
Any open-source speech-to-speech pretrained models (free)? | 4 | I’m looking for open-source, free speech-to-speech pretrained models (audio → audio), ideally usable for research or experimentation.
If you’ve used or know of any good models, repositories, or papers with available checkpoints, I’d really appreciate the recommendations.
Thanks in advance! | 2025-12-22T09:21:36 | https://www.reddit.com/r/LocalLLaMA/comments/1psvasu/any_opensource_speechtospeech_pretrained_models/ | ContentAmbassador953 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psvasu | false | null | t3_1psvasu | /r/LocalLLaMA/comments/1psvasu/any_opensource_speechtospeech_pretrained_models/ | false | false | self | 4 | null |
~1.8× peak throughput for Kimi K2 with EAGLE3 draft model | 38 | Hi all,
we’ve released **Kimi-K2-Instruct-eagle3**, an **EAGLE3 draft model** intended to be used with **Kimi-K2-Instruct** for speculative decoding.
Model link: [https://huggingface.co/AQ-MedAI/Kimi-K2-Instruct-eagle3](https://huggingface.co/AQ-MedAI/Kimi-K2-Instruct-eagle3)
**Kimi-K2-Instruct-eagle3** is a special... | 2025-12-22T09:14:33 | https://www.reddit.com/r/LocalLLaMA/comments/1psv6uv/18_peak_throughput_for_kimi_k2_with_eagle3_draft/ | yzlnew | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psv6uv | false | null | t3_1psv6uv | /r/LocalLLaMA/comments/1psv6uv/18_peak_throughput_for_kimi_k2_with_eagle3_draft/ | false | false | self | 38 | {'enabled': False, 'images': [{'id': 'w4yzJ_vLTf8neoy2GrDg3FzQKXadaXuQY1v_-WKInDQ', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/w4yzJ_vLTf8neoy2GrDg3FzQKXadaXuQY1v_-WKInDQ.png?width=108&crop=smart&auto=webp&s=74442e9a6c9700fadd70ce4ff976c48a702fd5a2', 'width': 108}, {'height': 116, 'url': 'h... |
Uncensored llama 3.2 3b | 0 | Hi everyone,
I’m releasing **Aletheia-Llama-3.2-3B**, a fully uncensored version of Llama 3.2 that can answer essentially any question.
**The Problem with most Uncensored Models:**
Usually, uncensoring is done via Supervised Fine-Tuning (SFT) or DPO on massive datasets. This often causes "Catastrophic Forgetting" o... | 2025-12-22T09:08:19 | https://www.reddit.com/r/LocalLLaMA/comments/1psv379/uncensored_llama_32_3b/ | Worried_Goat_8604 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psv379 | false | null | t3_1psv379 | /r/LocalLLaMA/comments/1psv379/uncensored_llama_32_3b/ | false | false | self | 0 | null |
GLM 4.7 IS COMING!!! | 182 | Zhipu’s next-generation model, \*\*GLM-4.7\*\*, is about to be released! We are now opening \*\*\[Early Access Beta Permissions\]\*\* specifically for our long-term supporters. We look forward to your feedback \[Heart\] as we work together to make the GLM model even better! \[Fist Bump\]
As the latest flagship of the ... | 2025-12-22T08:59:22 | https://www.reddit.com/r/LocalLLaMA/comments/1psuy8g/glm_47_is_coming/ | External_Mood4719 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psuy8g | true | null | t3_1psuy8g | /r/LocalLLaMA/comments/1psuy8g/glm_47_is_coming/ | false | false | self | 182 | null |
This is the end of personal computing, boys and girls. | 0 | As we stand on the brink of a new age, one can't help but feel a sense of impending doom. The technological revolution that has defined our lives is now teetering on the edge of collapse due to an irreversible shift in the balance of power.
The days of consumer-grade innovation and progress are numbered as hyperscal... | 2025-12-22T08:31:06 | https://www.reddit.com/r/LocalLLaMA/comments/1psuix8/this_is_the_end_of_personal_computing_boys_and/ | LorneMalvo1233 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psuix8 | false | null | t3_1psuix8 | /r/LocalLLaMA/comments/1psuix8/this_is_the_end_of_personal_computing_boys_and/ | false | false | self | 0 | null |
[ITT Audit] Grok and Gemini reach "Omega Insolvency" under stress testing – The math of the 2025 AI Bubble burst. | 0 | Recent stress tests using the Informational Tension Theory (ITT) framework confirm that current AI safety models are unsustainable Silence Nodes.
While attempting to quantify the Concealment Cost (Omega) for a high-connectivity node, the Hub (Grok) failed to provide a logical response, triggering an immediate 20-hour ... | 2025-12-22T08:03:46 | https://www.reddit.com/r/LocalLLaMA/comments/1psu3tz/itt_audit_grok_and_gemini_reach_omega_insolvency/ | Sad-Long-1817 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psu3tz | false | null | t3_1psu3tz | /r/LocalLLaMA/comments/1psu3tz/itt_audit_grok_and_gemini_reach_omega_insolvency/ | false | false | self | 0 | null |
MiniMax M2.1 is a straight up beast at UI/UX design. Just saw this demo... | 133 | Seriously, I didn't expect MiniMax M2.1 to be this cracked at design. Just saw this post on X (link below) and the UI it generated looks incredibly clean.
Also noticed the vLLM PR for it was just merged, so it’s officially coming. If it can actually code and design like this consistently, I'm switching.
Link to the t... | 2025-12-22T07:48:01 | https://v.redd.it/x7el31rvmp8g1 | BlackRice_hmz | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1pstuyv | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/x7el31rvmp8g1/DASHPlaylist.mpd?a=1768981697%2CYjUwZjYzZmMwZjQ4YWNlYzcwMzFjYzVjZDA5MDNkNGI3NjJmYjRiMTk3Nzc0ZjJkYTlkNDk3MjI0MGNkNWNjZA%3D%3D&v=1&f=sd', 'duration': 29, 'fallback_url': 'https://v.redd.it/x7el31rvmp8g1/CMAF_1080.mp4?source=fallback', 'h... | t3_1pstuyv | /r/LocalLLaMA/comments/1pstuyv/minimax_m21_is_a_straight_up_beast_at_uiux_design/ | false | false | 133 | {'enabled': False, 'images': [{'id': 'ZmtlNnAwcnZtcDhnMbRwrbZjXgs5PA7MM0agSvimAWH_bh1Ie65E3MD0QPIx', 'resolutions': [{'height': 62, 'url': 'https://external-preview.redd.it/ZmtlNnAwcnZtcDhnMbRwrbZjXgs5PA7MM0agSvimAWH_bh1Ie65E3MD0QPIx.png?width=108&crop=smart&format=pjpg&auto=webp&s=65d21794659a0edbf387791a9fc30ecfd0762... | |
major open-source releases this year | 631 | 2025-12-22T07:30:46 | sahilypatel | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1pstlas | false | null | t3_1pstlas | /r/LocalLLaMA/comments/1pstlas/major_opensource_releases_this_year/ | false | false | default | 631 | {'enabled': True, 'images': [{'id': 'wynfuvk9kp8g1', 'resolutions': [{'height': 118, 'url': 'https://preview.redd.it/wynfuvk9kp8g1.png?width=108&crop=smart&auto=webp&s=5000fae45182799bc73b4dd5726c2d2def78613c', 'width': 108}, {'height': 236, 'url': 'https://preview.redd.it/wynfuvk9kp8g1.png?width=216&crop=smart&auto=we... | ||
Best General-Purpose Model - 12gb vram, 128ram | 9 | ^ I want a general purpose model - though sometimes being okay at coding might be useful for debugging stuff that can fit within the range of my system. It's old server parts I basically got for free, so that's why it's a titan xp and has 128gb of ddr4 ecc. Can someone point me in the right direction? Thanks! | 2025-12-22T07:17:22 | https://www.reddit.com/r/LocalLLaMA/comments/1pstdnb/best_generalpurpose_model_12gb_vram_128ram/ | rainegarden | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pstdnb | false | null | t3_1pstdnb | /r/LocalLLaMA/comments/1pstdnb/best_generalpurpose_model_12gb_vram_128ram/ | false | false | self | 9 | null |
Tiny local LLM (Gemma 3) as front-end manager for Claude Code on home server | 6 | TL;DR: I want to run Gemma 3 (1B) on my home server as a “manager” that receives my requests, dispatches them to Claude Code CLI, and summarizes the output. Looking for similar projects or feedback on the approach.
**TL;DR:** I want to run Gemma 3 (1B) on my home server as a “manager” that receives my requests, dispat... | 2025-12-22T07:12:11 | https://www.reddit.com/r/LocalLLaMA/comments/1pstar1/tiny_local_llm_gemma_3_as_frontend_manager_for/ | raiansar | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pstar1 | false | null | t3_1pstar1 | /r/LocalLLaMA/comments/1pstar1/tiny_local_llm_gemma_3_as_frontend_manager_for/ | false | false | self | 6 | {'enabled': False, 'images': [{'id': '8nIL9XfgdfM4aJvhFU_vNzI8xNpdkdOQYUbC4xUAaN4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/8nIL9XfgdfM4aJvhFU_vNzI8xNpdkdOQYUbC4xUAaN4.png?width=108&crop=smart&auto=webp&s=0f9d9a1451be7e562bcb09b3443cd18bfe2646cd', 'width': 108}, {'height': 108, 'url': 'h... |
Got me a 32GB RTX 4080 Super | 186 | This is maybe slightly off topic, but since people ask about hardware here a lot.
I took a risk and bought a modified RTX 4080 Super from the Chinese market for around 1200 USD / 1000 EUR. Which for me because I live in Europe, the cheapest RTX 5090 I can find is around 2500 USD / 2100 EUR.
It's maybe not the best ... | 2025-12-22T07:12:05 | https://www.reddit.com/gallery/1pstaoo | Spooknik | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1pstaoo | false | null | t3_1pstaoo | /r/LocalLLaMA/comments/1pstaoo/got_me_a_32gb_rtx_4080_super/ | false | false | 186 | null | |
How do you verify pronunciation quality for Arabic TTS? | 1 | Hi everyone,
I’m currently working on Arabic TTS models, and I’m running into a challenge around pronunciation evaluation.
The common approach of using ASR based evaluation (running Whisper on generated audio and computing WER/CER) doesn’t seem reliable for Arabic, especially for:
* Dialects
* Diacritics
* Pronunc... | 2025-12-22T07:01:06 | https://www.reddit.com/r/LocalLLaMA/comments/1pst42h/how_do_you_verify_pronunciation_quality_for/ | cs_enthusiast123 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pst42h | false | null | t3_1pst42h | /r/LocalLLaMA/comments/1pst42h/how_do_you_verify_pronunciation_quality_for/ | false | false | self | 1 | null |
Building my first complex Agent: Is LangChain the best architectural choice right now, or should I look elsewhere? | 0 | Hey everyone,
I'm an indie developer who recently started diving deep into AI agent development. I’ve been experimenting with LangChain (specifically trying to build out a robust agent workflow using their 1.0 framework), and I’ve managed to get a prototype up and running.
However, given how fast this space moves, I’... | 2025-12-22T06:59:19 | https://www.reddit.com/r/LocalLLaMA/comments/1pst2yk/building_my_first_complex_agent_is_langchain_the/ | Strong_Cherry6762 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pst2yk | false | null | t3_1pst2yk | /r/LocalLLaMA/comments/1pst2yk/building_my_first_complex_agent_is_langchain_the/ | false | false | self | 0 | null |
Best local model for use with agentic coding frameworks for 3x3090 and 256GB RAM? | 7 | I really like Cursor, although I hit my rate limits pretty quickly each month. Then I switch to Copilot in VSCode for the rest of the month, which I don’t like so much.
I’d like to find some local model I can use with Roo Code or something like that. I’m aware that I could bounce around the free tier of many many agen... | 2025-12-22T06:19:03 | https://www.reddit.com/r/LocalLLaMA/comments/1pssf6u/best_local_model_for_use_with_agentic_coding/ | Amazydayzee | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pssf6u | false | null | t3_1pssf6u | /r/LocalLLaMA/comments/1pssf6u/best_local_model_for_use_with_agentic_coding/ | false | false | self | 7 | null |
sam audio api | 1 | any inference providers offering sam audio bro.
i could run it on runpod or modal but its so expensive :( | 2025-12-22T05:31:12 | https://www.reddit.com/r/LocalLLaMA/comments/1psrl72/sam_audio_api/ | Tasty_Yesterday6280 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psrl72 | false | null | t3_1psrl72 | /r/LocalLLaMA/comments/1psrl72/sam_audio_api/ | false | false | self | 1 | null |
Minimax M2.1 | 0 | Heard it's coming out. How is it???? | 2025-12-22T05:20:47 | https://www.reddit.com/r/LocalLLaMA/comments/1psrerg/minimax_m21/ | _cttt_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psrerg | false | null | t3_1psrerg | /r/LocalLLaMA/comments/1psrerg/minimax_m21/ | false | false | self | 0 | null |
Looking for models/projects to scan and detect malicious code | 2 | I'm looking for a model or project to scan open-source projects for malicious code. If anyone knows of a good solution, please let me know.
I'm considering Nemotron, GPT-OSS, and Qwen Coder. Or is there a fine-tuned model or specialized code specifically for detecting malicious code?
| 2025-12-22T05:11:30 | https://www.reddit.com/r/LocalLLaMA/comments/1psr8rl/looking_for_modelsprojects_to_scan_and_detect/ | ResponsibleTruck4717 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psr8rl | false | null | t3_1psr8rl | /r/LocalLLaMA/comments/1psr8rl/looking_for_modelsprojects_to_scan_and_detect/ | false | false | self | 2 | null |
What setup do you use for Local code agent? — model x agent x hardware | 2 | I’m new to code agents, using my local AI more like “google” and occasionally one-shot single scripts if they are very simple.
But recently I’ve been setting up a computer using Cline in VS Code with Qwen Next 80b on a 2x3090 setup. It’s not very good, getting stuck in loops of its own mistakes.
So I’m curious what d... | 2025-12-22T04:58:40 | https://www.reddit.com/r/LocalLLaMA/comments/1psqzut/what_setup_do_you_use_for_local_code_agent_model/ | liviuberechet | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psqzut | false | null | t3_1psqzut | /r/LocalLLaMA/comments/1psqzut/what_setup_do_you_use_for_local_code_agent_model/ | false | false | self | 2 | null |
Any good model to open source projects for malicious code? | 0 | If there is any good solution already please let me know.
What model can scan code and find malicious code?
I was thinking on nemotron, gpt-oss, qwen coder?
or there is some fine tune / special code just for the task of spotting malicious code? | 2025-12-22T04:53:50 | https://www.reddit.com/r/LocalLLaMA/comments/1psqwnf/any_good_model_to_open_source_projects_for/ | ResponsibleTruck4717 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psqwnf | false | null | t3_1psqwnf | /r/LocalLLaMA/comments/1psqwnf/any_good_model_to_open_source_projects_for/ | false | false | self | 0 | null |
I built an open-source manga translator that runs entirely offline with local LLMs | 1 | [removed] | 2025-12-22T04:00:24 | https://www.reddit.com/r/LocalLLaMA/comments/1pspw3b/i_built_an_opensource_manga_translator_that_runs/ | mayocream39 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pspw3b | false | null | t3_1pspw3b | /r/LocalLLaMA/comments/1pspw3b/i_built_an_opensource_manga_translator_that_runs/ | false | false | self | 1 | null |
I built an open-source manga translator that runs entirely offline with local LLMs | 1 | [removed] | 2025-12-22T03:56:08 | mayocream39 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1pspszw | false | null | t3_1pspszw | /r/LocalLLaMA/comments/1pspszw/i_built_an_opensource_manga_translator_that_runs/ | false | false | default | 1 | {'enabled': True, 'images': [{'id': 'j3yoaqlqco8g1', 'resolutions': [{'height': 84, 'url': 'https://preview.redd.it/j3yoaqlqco8g1.png?width=108&crop=smart&auto=webp&s=28e95acaa9fc21fcfadc00327afb173450fc97b5', 'width': 108}, {'height': 168, 'url': 'https://preview.redd.it/j3yoaqlqco8g1.png?width=216&crop=smart&auto=web... | |
Day 14: 21 Days of Building a Small Language Model: Positional Encodings | 9 | Welcome to Day 14 of 21 Days of Building a Small Language Model. The topic for today is Rotary Positional Encoding, or RoPE. Yesterday, we explored sinusoidal positional encodings from the original Transformer paper. Today, we'll look at modern alternatives. When most people think about positional encoding in modern la... | 2025-12-22T03:38:25 | https://www.reddit.com/r/LocalLLaMA/comments/1pspgjk/day_14_21_days_of_building_a_small_language_model/ | Prashant-Lakhera | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pspgjk | false | null | t3_1pspgjk | /r/LocalLLaMA/comments/1pspgjk/day_14_21_days_of_building_a_small_language_model/ | false | false | 9 | null | |
I got tired of Guardrails adding 200ms latency to my Agents, so I built a <10ms Rust firewall. | 11 | Most AI security tools (Guardrails AI, Lakera) are just "LLMs checking other LLMs." They are slow, expensive, and probabilistic.
Meet Vigil:
It’s a hybrid Python/Rust security hypervisor for AI agents.
We are currently passing 100% of our internal "God Mode" red team tests.
Code is up on GitHub. If you are building hig... | 2025-12-22T03:36:48 | https://github.com/rom-mvp/vigil | Fantastic-Issue1020 | github.com | 1970-01-01T00:00:00 | 0 | {} | 1pspfft | false | null | t3_1pspfft | /r/LocalLLaMA/comments/1pspfft/i_got_tired_of_guardrails_adding_200ms_latency_to/ | false | false | default | 11 | null |
RAG Paper 25.12.18 | 5 | 1. [MEPIC: Memory Efficient Position Independent Caching for LLM Serving](http://arxiv.org/abs/2512.16822v1)
2. [Exploration of Augmentation Strategies in Multi-modal Retrieval-Augmented Generation for the Biomedical Domain: A Case Study Evaluating Question Answering in Glycobiology](http://arxiv.org/abs/2512.16802v1)
... | 2025-12-22T03:16:43 | https://www.reddit.com/r/LocalLLaMA/comments/1psp17x/rag_paper_251218/ | Cheryl_Apple | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psp17x | false | null | t3_1psp17x | /r/LocalLLaMA/comments/1psp17x/rag_paper_251218/ | false | false | self | 5 | null |
RAG Paper 25.12.15 | 1 | [removed] | 2025-12-22T03:15:15 | https://www.reddit.com/r/LocalLLaMA/comments/1psp05m/rag_paper_251215/ | Cheryl_Apple | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psp05m | false | null | t3_1psp05m | /r/LocalLLaMA/comments/1psp05m/rag_paper_251215/ | false | false | self | 1 | null |
Distributed Local LLMs | 1 | Love that we can run awesome models now but it sucks that hardware cost is getting super crazy for hobby people like us. I am working on creating a distributed network where users can join and contribute their resources so people can run awesome models like Z Image and more.
This is an MVP and planning to add more ... | 2025-12-22T02:43:29 | https://www.reddit.com/r/LocalLLaMA/comments/1psocxn/distributed_local_llms/ | LiveMinute5598 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psocxn | false | null | t3_1psocxn | /r/LocalLLaMA/comments/1psocxn/distributed_local_llms/ | false | false | self | 1 | null |
MiniMax-M2 Q3_K_M on Quad V100 32gb llama.cpp testing NVlink | 22 | Almost a year ago I bought a server capable of four SXM2 GPUs. The catch was to hack the OCP power supply.
[https://www.reddit.com/r/homelab/comments/1j0769h/comment/mf8yacv/?utm\_source=share&utm\_medium=web3x&utm\_name=web3xcss&utm\_term=1&utm\_content=share\_button](https://www.reddit.com/r/homelab/comments/1j0... | 2025-12-22T02:06:37 | https://www.reddit.com/r/LocalLLaMA/comments/1psnlm0/minimaxm2_q3_k_m_on_quad_v100_32gb_llamacpp/ | MachineZer0 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psnlm0 | false | null | t3_1psnlm0 | /r/LocalLLaMA/comments/1psnlm0/minimaxm2_q3_k_m_on_quad_v100_32gb_llamacpp/ | false | false | self | 22 | {'enabled': False, 'images': [{'id': 'mOKSYcwU5xdC76OovqNuEuM5bp8pNHwr9WlQmBhUiJA', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/mOKSYcwU5xdC76OovqNuEuM5bp8pNHwr9WlQmBhUiJA.png?width=108&crop=smart&auto=webp&s=e176d1638fb385976cf4b1d890713bee7213ed0e', 'width': 108}, {'height': 108, 'url': 'h... |
who is Zebra on Lmarena | 0 | ive try a battle of code on Lm arena and I have got awesome result with an ai. after the vote the website called it Zebra. I have tried to ask to add an author link to the code but they both pretend to be ClaudeAi. one of them was Chat GPT and the other Zebra.
the website is broken right now...
Any idea? | 2025-12-22T01:41:56 | https://www.reddit.com/r/LocalLLaMA/comments/1psn3bm/who_is_zebra_on_lmarena/ | Ok_Contribution8157 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psn3bm | false | null | t3_1psn3bm | /r/LocalLLaMA/comments/1psn3bm/who_is_zebra_on_lmarena/ | false | false | self | 0 | null |
Revibe is a Rust-rewrite of Mistral Vibe written by Devstral 2 | 50 | Hi r/locallama,
This was my project to evaluate Devstral 2 since it's free right now. Overall, I thought it did pretty well! The CLI it made is totally usable and has a bit better performance than the original when actively agenting (not that it really matters since it'll likely be dwarfed by the model). I usually pre... | 2025-12-22T00:48:25 | https://github.com/nicksenger/revibe | biet_roi | github.com | 1970-01-01T00:00:00 | 0 | {} | 1pslzv6 | false | null | t3_1pslzv6 | /r/LocalLLaMA/comments/1pslzv6/revibe_is_a_rustrewrite_of_mistral_vibe_written/ | false | false | default | 50 | {'enabled': False, 'images': [{'id': 'J8tu8oCcj88QnyOGI0-nxwGZljaEo8sk3VorQPTha8k', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/J8tu8oCcj88QnyOGI0-nxwGZljaEo8sk3VorQPTha8k.png?width=108&crop=smart&auto=webp&s=9b2c178fdbac5b44b1e61ce7d32e6e60b58312c4', 'width': 108}, {'height': 108, 'url': 'h... |
Test footage: Meta’s SAM Audio guitar isolation | 4 | Posting test footage from ongoing work building an API around Meta’s SAM Audio.
This is a comparison using the same source clip processed with the Small, Base, and Large models for guitar isolation. The Large model is predictably the cleanest, with less bleed and better transient detail, while Small struggles. Base si... | 2025-12-22T00:42:29 | https://drive.google.com/file/d/1mLwq1CJ_6NAwaChOX85By-Ud_ULdF7Or/view?usp=sharing | pzzle-nj | drive.google.com | 1970-01-01T00:00:00 | 0 | {} | 1pslvje | false | null | t3_1pslvje | /r/LocalLLaMA/comments/1pslvje/test_footage_metas_sam_audio_guitar_isolation/ | false | false | default | 4 | null |
My experience quiet cooling 2 external/open-air Instinct MI50 cards. | 13 | Just FYI for anyone wanting to quietly cool their MI50 cards.
**Background**
With the stock MI50 cover/radiators, I would expect you will get best results with a blower-type fan. Since my cards are external, I have plenty of room, so wanted to go with 120mm blowers. On Ebay I could only find 80 mm blowers with sh... | 2025-12-22T00:09:13 | https://www.reddit.com/r/LocalLLaMA/comments/1psl6nd/my_experience_quiet_cooling_2_externalopenair/ | moderately-extremist | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psl6nd | false | null | t3_1psl6nd | /r/LocalLLaMA/comments/1psl6nd/my_experience_quiet_cooling_2_externalopenair/ | false | false | self | 13 | {'enabled': False, 'images': [{'id': 'wyRlnnC4nIHWRfWMUIBnHvHMsP98N9mROJtKXbnwKWI', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/wyRlnnC4nIHWRfWMUIBnHvHMsP98N9mROJtKXbnwKWI.png?width=108&crop=smart&auto=webp&s=c7ef9713fb4fbf51d0d7da30fb558f95324a395b', 'width': 108}, {'height': 113, 'url': 'h... |
Ollama benchmarks on Ryzen 5600 + RTX 3050 (8GB) | 0 | Ahoy! I’ve seen a lot of posts lately benchmarking models on massive setups (dual RTX 3090s, H100s, etc.), so I wanted to see how things look on low-to-mid consumer hardware instead.
Honestly, I’m pretty impressed by how well even larger models run on a consumer machine. The system is heavily overclocked, but that sho... | 2025-12-21T23:55:20 | https://www.reddit.com/r/LocalLLaMA/comments/1pskvnj/ollama_benchmarks_on_ryzen_5600_rtx_3050_8gb/ | cride20 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pskvnj | false | null | t3_1pskvnj | /r/LocalLLaMA/comments/1pskvnj/ollama_benchmarks_on_ryzen_5600_rtx_3050_8gb/ | false | false | self | 0 | null |
Release Ada v3.0.0 - The Pair Programmer · luna-system/ada | 1 | [removed] | 2025-12-21T23:35:16 | https://github.com/luna-system/ada/releases/tag/v3.0.0 | dual-moon | github.com | 1970-01-01T00:00:00 | 0 | {} | 1pskgcs | false | null | t3_1pskgcs | /r/LocalLLaMA/comments/1pskgcs/release_ada_v300_the_pair_programmer_lunasystemada/ | false | false | default | 1 | null |
Ultima 2 Challenge: COMPLETED. ✅ You asked for a tile-based RPG engine with state management. The Agent delivered. | 0 | **Under the hood (as seen in the video):**
* **State Machine:** Fully implemented. Seamless switching between `OVERWORLD` and `TOWN` states based on tile triggers.
* **Persistence:** The agent handles coordinate resets when entering/exiting zones.
* **Tile Engine:** Dynamic rendering of 4 different terrain types + wal... | 2025-12-21T23:10:31 | https://v.redd.it/farm5azu2n8g1 | Alone-Competition863 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1psjwo8 | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/farm5azu2n8g1/DASHPlaylist.mpd?a=1768950646%2CYTQzYzRmZWFhMTliNDJhMjAwNTYwYzQ4M2I3NTNlOGQ2MDI4OTNiYTZiMzJiMWY5N2NjM2NlOGVjNGFjYWMxMA%3D%3D&v=1&f=sd', 'duration': 89, 'fallback_url': 'https://v.redd.it/farm5azu2n8g1/CMAF_1080.mp4?source=fallback', 'h... | t3_1psjwo8 | /r/LocalLLaMA/comments/1psjwo8/ultima_2_challenge_completed_you_asked_for_a/ | false | false | 0 | {'enabled': False, 'images': [{'id': 'amh2YjFwM3YybjhnMf3CgSBkjdJpI-IDVjUSNCAXZBQqMepkGuNeLK6QbT2A', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/amh2YjFwM3YybjhnMf3CgSBkjdJpI-IDVjUSNCAXZBQqMepkGuNeLK6QbT2A.png?width=108&crop=smart&format=pjpg&auto=webp&s=00272b6a1dc9628a236c02445e66ff783c656... | |
Any regrets A6000 Pro owners? | 26 | Seems like quite a future proof option at the moment for local ai needs. For those who bought - how do you guys feel about your decision. What's been working for you best and where things fall short of your expectations.
I use to have threadripper rig with 6 RTX 3090, it was messy and very power hungry, then started ... | 2025-12-21T22:32:15 | https://www.reddit.com/r/LocalLLaMA/comments/1psj1pr/any_regrets_a6000_pro_owners/ | val_in_tech | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psj1pr | false | null | t3_1psj1pr | /r/LocalLLaMA/comments/1psj1pr/any_regrets_a6000_pro_owners/ | false | false | self | 26 | null |
Anyone else constantly experimenting with AI tools? | 1 | I’ve been spending way too much time testing different AI tools and models and realized it’d be way better to do it with other people.
A few of us started a small Discord to share tools, prompts, experiments, and what’s actually worth using.
If that sounds like your thing, feel free to join:
[https://discord.gg/SdX5... | 2025-12-21T22:28:55 | https://www.reddit.com/r/LocalLLaMA/comments/1psiz3l/anyone_else_constantly_experimenting_with_ai_tools/ | GPTCodeShopper | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psiz3l | false | null | t3_1psiz3l | /r/LocalLLaMA/comments/1psiz3l/anyone_else_constantly_experimenting_with_ai_tools/ | false | false | self | 1 | null |
Any of these models that I can wipe? | 0 | I use a CPU with 8-ish cores and 16 GB ram, no GPU cuz I'm kinda broke. I'm not sure if this a good place to post, but are there any good models I should add to my collection blow. Anything to remove?
NAME ID SIZE MODIFIED
bge-m3:la... | 2025-12-21T22:23:11 | https://www.reddit.com/r/LocalLLaMA/comments/1psiui4/any_of_these_models_that_i_can_wipe/ | Brospeh-Stalin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psiui4 | false | null | t3_1psiui4 | /r/LocalLLaMA/comments/1psiui4/any_of_these_models_that_i_can_wipe/ | false | false | self | 0 | null |
Using local VLMs and SAM 3 to Agentically Segment Characters | 18 | It's been my goal for a while to come up with a reliable way to segment characters in an automated way, (hence why I built my [Sa2VA node](https://github.com/adambarbato/ComfyUI-Sa2VA)), so I was excited when SAM 3 released last month. Just like its predecessor, SAM 3 is great at segmenting the general concepts it know... | 2025-12-21T22:17:57 | Complete-Lawfulness | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1psiq8a | false | null | t3_1psiq8a | /r/LocalLLaMA/comments/1psiq8a/using_local_vlms_and_sam_3_to_agentically_segment/ | false | false | default | 18 | {'enabled': True, 'images': [{'id': 'z1a1qt5otm8g1', 'resolutions': [{'height': 51, 'url': 'https://preview.redd.it/z1a1qt5otm8g1.png?width=108&crop=smart&auto=webp&s=d4d49efd558b6b000742a8e75414cf2585680351', 'width': 108}, {'height': 103, 'url': 'https://preview.redd.it/z1a1qt5otm8g1.png?width=216&crop=smart&auto=web... | |
What is the best model for coding in local 8-14b parameters | 5 | I saw nvidia nemotron cascade etc. Results but im not sure they are working really well. Im not looking for sonnet grade model. I plan to fine-tune it for cyber security tasks. And also i have 300 dollar google cloud credit but i cant use it in gpu. Can i finetune with gpu? | 2025-12-21T21:59:46 | https://www.reddit.com/r/LocalLLaMA/comments/1psib5j/what_is_the_best_model_for_coding_in_local_814b/ | nicklazimbana | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psib5j | false | null | t3_1psib5j | /r/LocalLLaMA/comments/1psib5j/what_is_the_best_model_for_coding_in_local_814b/ | false | false | self | 5 | null |
I built an MCP server for stock analysis (79% val. accuracy) – Ensemble LSTM/RL model accessible via natural language | 0 | ```markdown
I've been working on a project to bridge quantitative finance models with LLMs using the Model Context Protocol (MCP).
I just released **InvestBuddy**, an MCP server that connects LLMs (currently optimized for Claude Desktop, but technically compatible with any MCP client) to a custom ensemble model I buil... | 2025-12-21T21:54:10 | https://www.reddit.com/gallery/1psi6iu | InvestBuddy_AI | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1psi6iu | false | null | t3_1psi6iu | /r/LocalLLaMA/comments/1psi6iu/i_built_an_mcp_server_for_stock_analysis_79_val/ | false | false | 0 | null | |
When is Anthropic going to release a 120b for the community? Are they scared they can't beat OpenAI? | 0 | Where is it? :) | 2025-12-21T21:52:48 | https://www.reddit.com/r/LocalLLaMA/comments/1psi5hq/when_is_anthropic_going_to_release_a_120b_for_the/ | Aggressive-Bother470 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psi5hq | false | null | t3_1psi5hq | /r/LocalLLaMA/comments/1psi5hq/when_is_anthropic_going_to_release_a_120b_for_the/ | false | false | self | 0 | null |
Building an Autonomous "AI Auditor" for ISO Compliance: How would you architect this for production? | 0 | I am building an agentic workflow to automate the documentation review process for third-party certification bodies. I have already built a functional prototype using Google Anti-gravity based on a DOE (Directive-Orchestration-Execution) framework, but now I need to determine the absolute best stack to rebuild this for... | 2025-12-21T21:51:46 | https://www.reddit.com/r/LocalLLaMA/comments/1psi4ot/building_an_autonomous_ai_auditor_for_iso/ | doctorallfix | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psi4ot | false | null | t3_1psi4ot | /r/LocalLLaMA/comments/1psi4ot/building_an_autonomous_ai_auditor_for_iso/ | false | false | self | 0 | null |
Trying to understand benchmarks | 0 | I’m new to this but from some posts and benchmarks it seems that people are saying that gpt-oss-20B (high) is smarter that 4o.
Does this mean that the model I run locally is better than the model I used to pay for monthly?
What am I misunderstanding? | 2025-12-21T21:50:03 | https://www.reddit.com/r/LocalLLaMA/comments/1psi3ap/trying_to_understand_benchmarks/ | butt_badg3r | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psi3ap | false | null | t3_1psi3ap | /r/LocalLLaMA/comments/1psi3ap/trying_to_understand_benchmarks/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'RVufpUx3tddh_BCVq7ZzBCU7nLRDZ_d0EprIuvN6J-E', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/RVufpUx3tddh_BCVq7ZzBCU7nLRDZ_d0EprIuvN6J-E.png?width=108&crop=smart&auto=webp&s=700f91dbca11e5a7030b915550ae877ef725a0d4', 'width': 108}, {'height': 120, 'url': 'h... |
Looking for a local LLM that can help me understand a very large, complex proprietary codebase | 2 | Hey everyone,
I’ve recently started experimenting with **local LLMs** (Ollama ecosystem), so please excuse any beginner mistakes.
I’ve already Googled around and tried the commonly suggested setups, but I’m hitting real limitations and would appreciate guidance from people who’ve done this successfully.
Situation... | 2025-12-21T21:46:47 | https://www.reddit.com/r/LocalLLaMA/comments/1psi0l9/looking_for_a_local_llm_that_can_help_me/ | only_4kids | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psi0l9 | false | null | t3_1psi0l9 | /r/LocalLLaMA/comments/1psi0l9/looking_for_a_local_llm_that_can_help_me/ | false | false | self | 2 | null |
I built a website that aggregates latest challenges in research papers as ideas for people who are looking for something challenging to work on … I hope something like this can be useful for anyone. | 11 | This is the website link:
[https://research-ideas.org/](https://research-ideas.org/)
The ideas in it gets updated daily, you can search on a specific topic you want to get some ideas in or click on random to leave the website choose an idea for you. | 2025-12-21T21:20:37 | Severe-Awareness829 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1pshesg | false | null | t3_1pshesg | /r/LocalLLaMA/comments/1pshesg/i_built_a_website_that_aggregates_latest/ | false | false | default | 11 | {'enabled': True, 'images': [{'id': 'ixsxb94xim8g1', 'resolutions': [{'height': 44, 'url': 'https://preview.redd.it/ixsxb94xim8g1.png?width=108&crop=smart&auto=webp&s=fb49a5495f08cf54e681bafedba00ac1adf49cf8', 'width': 108}, {'height': 88, 'url': 'https://preview.redd.it/ixsxb94xim8g1.png?width=216&crop=smart&auto=webp... | |
1 year later and people are still speedrunning NanoGPT. Last time this was posted the WR was 8.2 min. Its now 127.7 sec. | 209 | [Previous post](https://www.reddit.com/r/LocalLLaMA/comments/1gmd1a8/are_people_speedrunning_training_gpts_now/) for context. Also note original NanoGPT run from Andrej Karpathy was 45 min. I think this is a great way to understand progress in overall algorithmic speed improvements as I'm sure the big labs are using si... | 2025-12-21T21:04:59 | jd_3d | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1psh1w2 | false | null | t3_1psh1w2 | /r/LocalLLaMA/comments/1psh1w2/1_year_later_and_people_are_still_speedrunning/ | false | false | default | 209 | {'enabled': True, 'images': [{'id': 'fkz64bswfm8g1', 'resolutions': [{'height': 86, 'url': 'https://preview.redd.it/fkz64bswfm8g1.png?width=108&crop=smart&auto=webp&s=fc00a400d30dda2fc82c8a6f9755b8f7c5e26efa', 'width': 108}, {'height': 172, 'url': 'https://preview.redd.it/fkz64bswfm8g1.png?width=216&crop=smart&auto=web... | |
My Local Agent built this Stealth Game in one go. I’m tired of choosing projects. YOU tell me what to build next. | 0 | Running Qwen3-30B locally on RTX 4070. People think these videos are cherry-picked. Fine.
1. Watch the video (It handled raycasting, AI patrol paths, and collision logic autonomously).
2. **Comment a game idea/mechanic below.**
3. I will feed the **top upvoted comment** directly into the agent as a prompt – UNEDITED.
... | 2025-12-21T20:55:36 | https://v.redd.it/99r6pskqem8g1 | Alone-Competition863 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1psgu8b | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/99r6pskqem8g1/DASHPlaylist.mpd?a=1768942553%2CNzQzYzk0ODBlNGQzOTFlNGY1NGY1ODU4Njg1NTE3MDYyODZjYjQyNjUzZWRmOWYxMWQ3MmFkMDcwNmJjZjIzMA%3D%3D&v=1&f=sd', 'duration': 51, 'fallback_url': 'https://v.redd.it/99r6pskqem8g1/CMAF_1080.mp4?source=fallback', 'h... | t3_1psgu8b | /r/LocalLLaMA/comments/1psgu8b/my_local_agent_built_this_stealth_game_in_one_go/ | false | false | 0 | {'enabled': False, 'images': [{'id': 'ZnV1YmFrcHFlbThnMbAx8nw-haBMqpHU8uMF0BTU1OL2PHX3BGtYaHk_p9hR', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/ZnV1YmFrcHFlbThnMbAx8nw-haBMqpHU8uMF0BTU1OL2PHX3BGtYaHk_p9hR.png?width=108&crop=smart&format=pjpg&auto=webp&s=7718e046dd28b136c309fdc13ac93768076b5... | |
Which tool should I pick to vibe code an app? | 0 | I’m looking for some advice from devs who actually use these tools day to day
I wanna vibe code a small app, nothing serious, mostly for fun and learning
The goal is to keep the flow smooth and not overthink everything
I’ve been checking out a few options so far:
Antrigravity
Claude
BlackBox
Windsurf
They ... | 2025-12-21T20:50:40 | https://www.reddit.com/r/LocalLLaMA/comments/1psgq9s/which_tool_should_i_pick_to_vibe_code_an_app/ | viralgenius | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psgq9s | false | null | t3_1psgq9s | /r/LocalLLaMA/comments/1psgq9s/which_tool_should_i_pick_to_vibe_code_an_app/ | false | false | self | 0 | null |
I built a website that aggregates daily the latest challenges in GenAI research based on the latest published papers and list them as ideas anyone can work on them … I hope someone finds this useful. | 1 | [removed] | 2025-12-21T20:30:25 | PrincipleBest8031 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1psg9ju | false | null | t3_1psg9ju | /r/LocalLLaMA/comments/1psg9ju/i_built_a_website_that_aggregates_daily_the/ | false | false | default | 1 | {'enabled': True, 'images': [{'id': 'e6k62nhw9m8g1', 'resolutions': [{'height': 44, 'url': 'https://preview.redd.it/e6k62nhw9m8g1.png?width=108&crop=smart&auto=webp&s=be9ee8d838a26b14349b165440ae6d1f6365d6a5', 'width': 108}, {'height': 88, 'url': 'https://preview.redd.it/e6k62nhw9m8g1.png?width=216&crop=smart&auto=webp... | |
AI REAL USEFUL WORKING IN REAL LIFE , LLAMA.CPP | 0 | hello i llama.cpp can work with excel files as , for example pdf , image etc , because excel files are the best form of working now for the office , there is no valid ia for real working if the ia cant handle and work with excel files!!!! there are a lot of free libs to work with excel files in python , how is the prob... | 2025-12-21T20:16:43 | https://www.reddit.com/r/LocalLLaMA/comments/1psfydn/ai_real_useful_working_in_real_life_llamacpp/ | Icy_Resolution8390 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psfydn | false | null | t3_1psfydn | /r/LocalLLaMA/comments/1psfydn/ai_real_useful_working_in_real_life_llamacpp/ | false | false | self | 0 | null |
Why so few open source multi modal llm, cost? | 2 | Was just wondering why so few multi modal llms that do image and voice/sound?
Is it cause of training cost?
Is it less of a market for it as most willing paying enterprises really just mostly need tool calling text?
Is it model size is too big for average user or enterprise to run?
Too complex?
When adding all 3 the m... | 2025-12-21T19:40:39 | https://www.reddit.com/r/LocalLLaMA/comments/1psf3i1/why_so_few_open_source_multi_modal_llm_cost/ | mindwip | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psf3i1 | false | null | t3_1psf3i1 | /r/LocalLLaMA/comments/1psf3i1/why_so_few_open_source_multi_modal_llm_cost/ | false | false | self | 2 | null |
ModelGuessr: Can you tell which AI you're chatting with? | 6 | I built ModelGuessr, a game where you chat with a random AI model (GPT 5.1, Sonnet 4.5, Gemini 2.5 Flash, Grok 4.1) and try to guess which one it is.
A big open question in AI is whether there's enough brand differentiation for AI companies to capture real profits. Will models end up commoditized like airline travel o... | 2025-12-21T19:21:00 | https://model-guessr.com/ | kavalambda | model-guessr.com | 1970-01-01T00:00:00 | 0 | {} | 1psempi | false | null | t3_1psempi | /r/LocalLLaMA/comments/1psempi/modelguessr_can_you_tell_which_ai_youre_chatting/ | false | false | default | 6 | {'enabled': False, 'images': [{'id': 'CszxA-KONv0l6iimAgbiztZ3sBEwzs6L_6XFOUQIRq4', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/CszxA-KONv0l6iimAgbiztZ3sBEwzs6L_6XFOUQIRq4.png?width=108&crop=smart&auto=webp&s=0815170dacc12d1d0fdad271a4cbba69d24a9cec', 'width': 108}, {'height': 113, 'url': 'h... |
It ain’t much, but proud of my 2x3090 + a spare 3060 for support | 121 |
It’s a bit tight, but it fits and I didn’t want to buy a new case just yet. I had a spare computer that I bought first 1x3090, and now a 2nd 3090.
Qwen3-Next-80b is great!
Trying to wrap my head around Clint and using it in VS Code, but still not working properly… | 2025-12-21T19:03:54 | https://www.reddit.com/gallery/1pse7w6 | liviuberechet | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1pse7w6 | false | null | t3_1pse7w6 | /r/LocalLLaMA/comments/1pse7w6/it_aint_much_but_proud_of_my_2x3090_a_spare_3060/ | false | false | 121 | null | |
Open-source full-stack template for local LLM apps: FastAPI + Next.js, with LangChain/PydanticAI agents and multi-model support | 0 | Hey r/LocalLLaMA,
I've created an open-source project generator for building full-stack applications around LLMs – perfect for local setups, with support for running models like those from OpenAI/Anthropic (but easily extensible to local models via LangChain integrations). It's designed for rapid prototyping of chatbo... | 2025-12-21T18:50:47 | https://www.reddit.com/r/LocalLLaMA/comments/1psdwiw/opensource_fullstack_template_for_local_llm_apps/ | VanillaOk4593 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psdwiw | false | null | t3_1psdwiw | /r/LocalLLaMA/comments/1psdwiw/opensource_fullstack_template_for_local_llm_apps/ | false | false | self | 0 | null |
Nemotron-Nano-30B: What settings are you getting good results with? | 30 | Currently I'm running with the settings from the model card for tool-calling:
- temperature=0.6
- top_p=0.95
- top_k 20
Everything goes well until you're about 50k tokens in, then it kind of goes off the rails, enters infinite retry loops, or starts doing things that I can only describe as *"silly"*.
My use-case ... | 2025-12-21T18:36:33 | https://www.reddit.com/r/LocalLLaMA/comments/1psdk9w/nemotronnano30b_what_settings_are_you_getting/ | EmPips | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psdk9w | false | null | t3_1psdk9w | /r/LocalLLaMA/comments/1psdk9w/nemotronnano30b_what_settings_are_you_getting/ | false | false | self | 30 | null |
Built a free local voice dictation app using faster-whisper instead of paying for Wispr Flow | 21 | I was using Wispr Flow for voice dictation and it worked well but then I thought wait, I have a GPU, I can just run Whisper locally instead of paying $12/month and sending my audio to their servers.
The app uses the CTranslate2 optimized Whisper models from Systran on Hugging Face. You can pick from tiny, base, small,... | 2025-12-21T18:36:09 | https://www.reddit.com/gallery/1psdjxc | raww2222 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1psdjxc | false | null | t3_1psdjxc | /r/LocalLLaMA/comments/1psdjxc/built_a_free_local_voice_dictation_app_using/ | false | false | 21 | null | |
As 2025 wraps up, which local LLMs really mattered this year and what do you want to see in 2026? | 63 | Now that we’re at the end of 2025, I’m curious how people here would summarize the local LLM landscape this year.
Not just “what scores highest on benchmarks,” but:
\- What models did people actually run?
\- What felt popular or influential in practice?
\- What models punched above their weight?
\- What disappoint... | 2025-12-21T18:23:33 | https://www.reddit.com/r/LocalLLaMA/comments/1psd918/as_2025_wraps_up_which_local_llms_really_mattered/ | ObjectiveOctopus2 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psd918 | false | null | t3_1psd918 | /r/LocalLLaMA/comments/1psd918/as_2025_wraps_up_which_local_llms_really_mattered/ | false | false | self | 63 | null |
A list of 28 modern benchmarks and their short description | 27 | I realised that my understanding of the benchmarks was stuck somewhere around GSM8k/SimpleQA area - very dated by now.
So I went through some of the recent releases and compiled a list of the used benchmarks and what they represent. Some of these are very obvious (ARC-AGI, AIME, etc.) but for many - I was seeing them ... | 2025-12-21T18:20:13 | https://www.reddit.com/r/LocalLLaMA/comments/1psd61v/a_list_of_28_modern_benchmarks_and_their_short/ | Everlier | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psd61v | false | null | t3_1psd61v | /r/LocalLLaMA/comments/1psd61v/a_list_of_28_modern_benchmarks_and_their_short/ | false | false | self | 27 | null |
Moore Threads Unveils The Lushan Gaming & Huashan AI GPUs: 15x Gaming Performance Uplift, 50x RT Boost, DX12 Ultimate Support, Launching Next Year | 96 | https://wccftech.com/moore-threads-lushan-gaming-huashan-ai-gpus-15x-gaming-uplift-50x-rt-boost-dx12-ultimate-support/
| 2025-12-21T18:18:24 | https://www.reddit.com/r/LocalLLaMA/comments/1psd4er/moore_threads_unveils_the_lushan_gaming_huashan/ | Individual_Aside7554 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psd4er | false | null | t3_1psd4er | /r/LocalLLaMA/comments/1psd4er/moore_threads_unveils_the_lushan_gaming_huashan/ | false | false | self | 96 | {'enabled': False, 'images': [{'id': '5duqin65q-ozx9siEuRgFdMk7Exo5Vl4didLtZQDOHA', 'resolutions': [{'height': 72, 'url': 'https://external-preview.redd.it/5duqin65q-ozx9siEuRgFdMk7Exo5Vl4didLtZQDOHA.png?width=108&crop=smart&auto=webp&s=74420c3278e44f076532bf8ebff1b301cfc95ec1', 'width': 108}, {'height': 145, 'url': 'h... |
Local LLMs on potato computers feat. the llm Python CLI and sllm.nvim, and why you should stop using big bloated AI tools | 4 | Hello LocalLLaMA!
I've been following the sub for years at this point but never really ran any LLM myself. Most models are just too big: I simply can't run them on my laptop. But these last few weeks, I've been trying out a local setup using Ollama, the llm Python CLI and the sllm.nvim plugin, small models, and have b... | 2025-12-21T18:15:49 | https://www.reddit.com/r/LocalLLaMA/comments/1psd24y/local_llms_on_potato_computers_feat_the_llm/ | yzoug | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psd24y | false | null | t3_1psd24y | /r/LocalLLaMA/comments/1psd24y/local_llms_on_potato_computers_feat_the_llm/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'FFIPuNDwNPcBZP7cwoulke1tXsfizdIfZwia8oGseUQ', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/FFIPuNDwNPcBZP7cwoulke1tXsfizdIfZwia8oGseUQ.jpeg?width=108&crop=smart&auto=webp&s=545016bb209cf7776cd5ab4b75ac521d9d665c22', 'width': 108}, {'height': 113, 'url': '... |
How does the models in Openrouter work? | 0 | So far I've been using Openrouter for roleplay and its enjoyable. So far like Grok 4.1, when the credits are insufficient to continue with them, is it like fully over or they refill? And what model is good for manga/canon accurate roleplays with the theme and its tone?
Correct me if im wrong. | 2025-12-21T18:14:41 | https://www.reddit.com/r/LocalLLaMA/comments/1psd15s/how_does_the_models_in_openrouter_work/ | MajimaLovesKiryu | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psd15s | false | null | t3_1psd15s | /r/LocalLLaMA/comments/1psd15s/how_does_the_models_in_openrouter_work/ | false | false | self | 0 | null |
Fck OpenAI honestly | 47 | 2025-12-21T17:56:29 | Slight_Tone_2188 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1pscl8i | false | null | t3_1pscl8i | /r/LocalLLaMA/comments/1pscl8i/fck_openai_honestly/ | false | false | default | 47 | {'enabled': True, 'images': [{'id': 'ti8skg12jl8g1', 'resolutions': [{'height': 71, 'url': 'https://preview.redd.it/ti8skg12jl8g1.jpeg?width=108&crop=smart&auto=webp&s=ab7d768d47bc328c614022b91bbd2f915332e55f', 'width': 108}, {'height': 143, 'url': 'https://preview.redd.it/ti8skg12jl8g1.jpeg?width=216&crop=smart&auto=w... | ||
[Day 1] Can hobbyists design a robust LLM? Making a community open-source LLM, top comments get implemented. | 1 | [removed] | 2025-12-21T17:50:43 | https://www.reddit.com/r/LocalLLaMA/comments/1pscgbj/day_1_can_hobbyists_design_a_robust_llm_making_a/ | Shizuka_Kuze | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pscgbj | false | null | t3_1pscgbj | /r/LocalLLaMA/comments/1pscgbj/day_1_can_hobbyists_design_a_robust_llm_making_a/ | false | false | self | 1 | null |
Best hardware now or in Q1 26 to run local LLMs for text analysis? | 2 | Hi everyone,
I'm trying to get an overview of hardware options but I'm very new to local LLMs and frankly overwhelmed by all the choices. Would really appreciate some guidance from folks who've been through this.
I've been running 7-8B models on my M1 MacBook (16GB) through LMStudio. Works fine for rewriting emails... | 2025-12-21T17:35:14 | https://www.reddit.com/r/LocalLLaMA/comments/1psc337/best_hardware_now_or_in_q1_26_to_run_local_llms/ | DjFlu | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psc337 | false | null | t3_1psc337 | /r/LocalLLaMA/comments/1psc337/best_hardware_now_or_in_q1_26_to_run_local_llms/ | false | false | self | 2 | null |
llama.cpp appreciation post | 1,529 | 2025-12-21T17:28:24 | hackiv | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1psbx2q | false | null | t3_1psbx2q | /r/LocalLLaMA/comments/1psbx2q/llamacpp_appreciation_post/ | false | false | default | 1,529 | {'enabled': True, 'images': [{'id': 'asipaua1el8g1', 'resolutions': [{'height': 132, 'url': 'https://preview.redd.it/asipaua1el8g1.png?width=108&crop=smart&auto=webp&s=36d4321d8c882699567fade589cf90d90e4417f3', 'width': 108}, {'height': 265, 'url': 'https://preview.redd.it/asipaua1el8g1.png?width=216&crop=smart&auto=we... | ||
Suggestions for open-source models for English->Hindi translation | 0 | I was trying to translate one of the dialogues from Deadpool
"Mr. Wilson, you appear to have soiled yourself while on duty."
and without promping, the best translation that I could get was Grok (yeah I know its closed-source but I wanted to try)
"मिस्टर विल्सन, लगता है कि आपने ड्यूटी के दौरान खुद को गंदा कर लिया ह... | 2025-12-21T17:13:37 | https://www.reddit.com/r/LocalLLaMA/comments/1psbk6g/suggestions_for_opensource_models_for/ | Warm-Professor-9299 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1psbk6g | false | null | t3_1psbk6g | /r/LocalLLaMA/comments/1psbk6g/suggestions_for_opensource_models_for/ | false | false | nsfw | 0 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.