Local Models Collection by salhif Aug 26 - unsloth/Qwen3.8-27B-GGUF 27B • Updated Aug 20 • 6.1M • 5.61k
Local LLM Engineering Notes Reproducible tools and technical notes on local LLM inference, GGUF, llama.cpp and AMD ROCm systems. Collection by redoracle Aug 26 - Running GGUF Inspector 🚀 Inspect GGUF model files locally in your browser Running Local LLM Systems Lab 🚀 Explore local LLM inference performance metrics redoracle/local-llm-engineering-notes Updated Aug 26
Qwen3-VL-8B video RLVR - GRPO checkpoint ladder Every published checkpoint of the 8B video-QA GRPO campaign, ranked by core-3 mean_accuracy (5,645 rows). Untrained base = 0.4426. Collection by ngqtrung Aug 26 - ngqtrung/video-8b-grpo-n16-warm-explore Video-Text-to-Text • 9B • Updated Aug 26 • 9 ngqtrung/video-8b-grpo-base Image-Text-to-Text • 9B • Updated Jun 22 • 14 ngqtrung/video-8b-grpo-ppexplore-n16k8 Image-Text-to-Text • 9B • Updated Jun 22 • 11 ngqtrung/video-8b-grpo-ppexplore Image-Text-to-Text • 9B • Updated Jun 22 • 7 • 1
Partial RoPE Analysis Models trained via GPT-NeoX for studying Partial RoPE. Collection by aflah Sep 1 - Fractional Rotation, Full Potential? Investigating Performance and Convergence of Partial RoPE Paper • 2603.11611 • Published Mar 12 aflah/Llama1BxFW_Edux2048x0pct Updated Aug 26 aflah/Llama1BxFW_Edux2048x4pct Updated Aug 26 aflah/Llama1BxFW_Edux2048x10pct Updated Aug 26
Fractional Rotation, Full Potential? Investigating Performance and Convergence of Partial RoPE Paper • 2603.11611 • Published Mar 12
VCL VibeBench Practical AI model comparisons you can inspect and re-run. Fun, Dev, and Score prompts plus maintainer results — not a blended leaderboard. Stop trust Collection by kondasviktor Aug 26 - Running VCL VibeBench ⚡ Practical AI model comparisons you can inspect. kondasviktor/vcl-vibebench Viewer • Updated Aug 25 • 57 • 33
raw_llms_for_fine_tuning Collection by Ramshrivastav Sep 24 - deepset/roberta-base-squad2 Question Answering • 0.1B • Updated Sep 24, 2024 • 429k • • 978 openai/whisper-small Automatic Speech Recognition • 0.2B • Updated Feb 29, 2024 • 4.38M • 646 google-t5/t5-large Translation • 0.7B • Updated Apr 6, 2023 • 226k • • 264 ProsusAI/finbert Text Classification • 0.1B • Updated 27 days ago • 3.27M • • 1.3k
TrustSQL TRUST-SQL is a tool-integrated multi-turn reinforcement-learning framework for Text-to-SQL over Unknown Schemas. Collection by AIJian Aug 27 - AIJian/TrustSQL-4B Text Generation • 4B • Updated Aug 27 • 31 AIJian/TrustSQL-8B Text Generation • 8B • Updated Aug 27 • 71 AIJian/TrustSQL-data Viewer • Updated Aug 27 • 71k • 263 AIJian/TrustSQL Reinforcement Learning • Updated Aug 27
Llama Collection by Sunsetvbhh Aug 26 - Guilherme34/Hermes-3-Llama-3.1-70B-Uncensored Text Generation • 71B • Updated Sep 27, 2025 • 92 • • 17
Guilherme34/Hermes-3-Llama-3.1-70B-Uncensored Text Generation • 71B • Updated Sep 27, 2025 • 92 • • 17
Local Models Collection by salhif Aug 26 - unsloth/Qwen3.8-27B-GGUF 27B • Updated Aug 20 • 6.1M • 5.61k
VCL VibeBench Practical AI model comparisons you can inspect and re-run. Fun, Dev, and Score prompts plus maintainer results — not a blended leaderboard. Stop trust Collection by kondasviktor Aug 26 - Running VCL VibeBench ⚡ Practical AI model comparisons you can inspect. kondasviktor/vcl-vibebench Viewer • Updated Aug 25 • 57 • 33
raw_llms_for_fine_tuning Collection by Ramshrivastav Sep 24 - deepset/roberta-base-squad2 Question Answering • 0.1B • Updated Sep 24, 2024 • 429k • • 978 openai/whisper-small Automatic Speech Recognition • 0.2B • Updated Feb 29, 2024 • 4.38M • 646 google-t5/t5-large Translation • 0.7B • Updated Apr 6, 2023 • 226k • • 264 ProsusAI/finbert Text Classification • 0.1B • Updated 27 days ago • 3.27M • • 1.3k
Local LLM Engineering Notes Reproducible tools and technical notes on local LLM inference, GGUF, llama.cpp and AMD ROCm systems. Collection by redoracle Aug 26 - Running GGUF Inspector 🚀 Inspect GGUF model files locally in your browser Running Local LLM Systems Lab 🚀 Explore local LLM inference performance metrics redoracle/local-llm-engineering-notes Updated Aug 26
TrustSQL TRUST-SQL is a tool-integrated multi-turn reinforcement-learning framework for Text-to-SQL over Unknown Schemas. Collection by AIJian Aug 27 - AIJian/TrustSQL-4B Text Generation • 4B • Updated Aug 27 • 31 AIJian/TrustSQL-8B Text Generation • 8B • Updated Aug 27 • 71 AIJian/TrustSQL-data Viewer • Updated Aug 27 • 71k • 263 AIJian/TrustSQL Reinforcement Learning • Updated Aug 27
Qwen3-VL-8B video RLVR - GRPO checkpoint ladder Every published checkpoint of the 8B video-QA GRPO campaign, ranked by core-3 mean_accuracy (5,645 rows). Untrained base = 0.4426. Collection by ngqtrung Aug 26 - ngqtrung/video-8b-grpo-n16-warm-explore Video-Text-to-Text • 9B • Updated Aug 26 • 9 ngqtrung/video-8b-grpo-base Image-Text-to-Text • 9B • Updated Jun 22 • 14 ngqtrung/video-8b-grpo-ppexplore-n16k8 Image-Text-to-Text • 9B • Updated Jun 22 • 11 ngqtrung/video-8b-grpo-ppexplore Image-Text-to-Text • 9B • Updated Jun 22 • 7 • 1
Llama Collection by Sunsetvbhh Aug 26 - Guilherme34/Hermes-3-Llama-3.1-70B-Uncensored Text Generation • 71B • Updated Sep 27, 2025 • 92 • • 17
Guilherme34/Hermes-3-Llama-3.1-70B-Uncensored Text Generation • 71B • Updated Sep 27, 2025 • 92 • • 17
Partial RoPE Analysis Models trained via GPT-NeoX for studying Partial RoPE. Collection by aflah Sep 1 - Fractional Rotation, Full Potential? Investigating Performance and Convergence of Partial RoPE Paper • 2603.11611 • Published Mar 12 aflah/Llama1BxFW_Edux2048x0pct Updated Aug 26 aflah/Llama1BxFW_Edux2048x4pct Updated Aug 26 aflah/Llama1BxFW_Edux2048x10pct Updated Aug 26
Fractional Rotation, Full Potential? Investigating Performance and Convergence of Partial RoPE Paper • 2603.11611 • Published Mar 12
Aug 26 
