Qwen/Qwen-Image-2.1-Turbo
Text-to-Image • 7B • Updated • 272
🏗️ Building on HF
aifeifei
aifeifei798
P(doom) <0.001%
AI & ML interests
roleplay
Recent Activity
liked a model about 2 hours ago
Qwen/Qwen-Image-2.1-Turbo liked a model about 24 hours ago
ISTA-DASLab/Qwen3-Coder-Next-RCO-pruned liked a model 1 day ago
ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUFOrganizations
liked a
model about 2 hours ago
liked a
model about 24 hours ago
liked a
model 1 day ago
updated a
model 2 days ago
liked a
model 2 days ago
You're the person i want to meet.
5
#1 opened 4 days ago
by 
BingoBird
published a
model 3 days ago
liked a
model 3 days ago
updated a
model 3 days ago
A privelege to discover this.
1
#1 opened 4 days ago
by BingoBird
Inquiry regarding ablation efficacy and distributional shift metrics
👍 1
4
#1 opened 6 months ago
by 
CosmossG
liked a
model 7 days ago
reacted to SeaWolf-AI's post with 👍 7 days ago
Post
6220
💻 Data-center AI, now on a laptop: POCKET-Darwin-180B
We're releasing a 4-bit GGUF build of Darwin-180B-RSI, #1 on seven official Hugging Face leaderboards (self-reported), that runs without a GPU.
📦 360 GB → 111 GB (4-bit GGUF, 4 files)
🖥️ No GPU: one server CPU (16 threads) at 18.4–21.0 tokens/s
💻 RTX 5060 laptop (8 GB VRAM) + 32 GB RAM: 4.17 tokens/s
🧊 128 GB mini PC: whole model in memory, no GPU needed
🎯 MMLU-Pro, 2,000 questions, paired: original 87.65% = 4-bit 87.65%
How?
· Only ~3B of 180B parameters are active per token (10 of 512 experts)
· llama.cpp streams just the needed experts from SSD, so 32 GB RAM is enough
· Graft quantization: we took the proven Unsloth UD-Q4_K_XL base build and swapped in only the 300 tensors our RSI training changed (300/300 verified)
Under the hood is Model-level Recursive Self-Improvement. The model solves verifiable problems, keeps only its own solutions that check out as correct, and trains on them. No human-written solutions or reasoning traces.
Built for teams that can't send data to an external cloud (defense, finance, public sector) to run a top-tier model fully offline.
📝 Article: https://huggingface.co/blog/FINAL-Bench/data-center-ai-now-on-a-laptop-pocket-darwin-180b
🤗 Model: FINAL-Bench/POCKET-Darwin-180B-GGUF
🧬 Original: FINAL-Bench/Darwin-180B-RSI
#Darwin #RSI #GGUF #llamacpp #OnDevice #MoE
We're releasing a 4-bit GGUF build of Darwin-180B-RSI, #1 on seven official Hugging Face leaderboards (self-reported), that runs without a GPU.
📦 360 GB → 111 GB (4-bit GGUF, 4 files)
🖥️ No GPU: one server CPU (16 threads) at 18.4–21.0 tokens/s
💻 RTX 5060 laptop (8 GB VRAM) + 32 GB RAM: 4.17 tokens/s
🧊 128 GB mini PC: whole model in memory, no GPU needed
🎯 MMLU-Pro, 2,000 questions, paired: original 87.65% = 4-bit 87.65%
How?
· Only ~3B of 180B parameters are active per token (10 of 512 experts)
· llama.cpp streams just the needed experts from SSD, so 32 GB RAM is enough
· Graft quantization: we took the proven Unsloth UD-Q4_K_XL base build and swapped in only the 300 tensors our RSI training changed (300/300 verified)
Under the hood is Model-level Recursive Self-Improvement. The model solves verifiable problems, keeps only its own solutions that check out as correct, and trains on them. No human-written solutions or reasoning traces.
Built for teams that can't send data to an external cloud (defense, finance, public sector) to run a top-tier model fully offline.
📝 Article: https://huggingface.co/blog/FINAL-Bench/data-center-ai-now-on-a-laptop-pocket-darwin-180b
🤗 Model: FINAL-Bench/POCKET-Darwin-180B-GGUF
🧬 Original: FINAL-Bench/Darwin-180B-RSI
#Darwin #RSI #GGUF #llamacpp #OnDevice #MoE
- 30 replies
liked 2
models 7 days ago
updated a
model 8 days ago
published a
model 8 days ago
published a
model 9 days ago
updated 2
models 9 days ago