LOCALS Collection by xnxnxnnxnxnxnnx9897867564x6x 13 days ago - openai-community/gpt2 Text Generation • 0.1B • Updated Feb 19, 2024 • 31.3M • 3.92k superwhisper/s1-mini Text Generation • 0.8B • Updated Aug 28 • 1.92k • 385 Nanbeige/Nanbeige4.2-3B-DSpark Text Generation • 0.8B • Updated Aug 31 • 445 • 29 Qwen/Qwen3-0.6B Text Generation • 0.8B • Updated Jul 26, 2025 • 21.4M • • 1.88k
Huihui Collection by dzenatoriusz Sep 3 - huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF Image-Text-to-Text • 27B • Updated 28 days ago • 3.83M • 1.8k
huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF Image-Text-to-Text • 27B • Updated 28 days ago • 3.83M • 1.8k
1pp One Persona Pretraining: 3 sizes × 3 pretraining conditions, base and SFT models Collection by Raghav-Singhal 1 day ago - Raghav-Singhal/1pp-1b-asst-base Text Generation • 1.0B • Updated Sep 4 • 16 Raghav-Singhal/1pp-0.5b-asst-base Text Generation • 0.6B • Updated Sep 4 • 17 Raghav-Singhal/1pp-0.5b-asst-sft Text Generation • 0.6B • Updated Sep 3 • 14 Raghav-Singhal/1pp-0.5b-raw-base Text Generation • 0.6B • Updated Sep 4 • 16
technical slang translation - dataset review Collection by nikavetshtein Sep 8 - cais/mmlu Viewer • Updated Mar 8, 2024 • 231k • 574k • 884 TIGER-Lab/MMLU-Pro Benchmark • Updated May 2 • 12.1k • 396k • 601 deepset/prompt-injections Viewer • Updated Jul 30, 2024 • 662 • 16.4k • 200 McGill-NLP/speech-translation-and-summarization Viewer • Updated Aug 12 • 10k • 517 • 6
first collection Collection by SumeroStudio Sep 3 - Running Agents Featured 1.2k Qwen3 Coder WebDev 🌍 1.2k Generate web page code from a description Running Featured 247 Gemma 4 WebGPU 🚀 247 Run Gemma 4 locally in-browser on WebGPU w/ Transformers.js Running Agents 77 Medical Diagnosis 📉 77 Classify symptoms into possible medical conditions Running on Zero Agents Featured 181 MarioGPT 🦀 181 Generate a playable Mario level from a text prompt
Running Featured 247 Gemma 4 WebGPU 🚀 247 Run Gemma 4 locally in-browser on WebGPU w/ Transformers.js
Running on Zero Agents Featured 181 MarioGPT 🦀 181 Generate a playable Mario level from a text prompt
Quantized Models Collection by systalyze Sep 3 - systalyze/gemma-4-26B-A4B-it-ExpertsINT4-FP8 Image-Text-to-Text • 26B • Updated Sep 4 • 303 • 2
To Try Later (3080 - 10GB) Collection by pkarath 2 days ago - XHToken/Spark-X2.5-4B Text Generation • 4B • Updated Sep 15 • 29.2k • 1.44k IFM/K2-Horizon-7B Text Generation • 9B • Updated 3 days ago • 84.4k • • 282 unsloth/Qwen3.5-9B-GGUF Image-Text-to-Text • 9B • Updated Mar 2 • 1.77M • 1.06k ornith-ai/Ornith-1.0-9B-GGUF Text Generation • 9B • Updated Jun 25 • 2.4M • 699
Scaling Ladder (optimized) — 3 sizes, 286M–897M, 200 TPP Speedrun architecture: 8 pretraining seeds/size, anneal marks every 10 TPP as revisions. Plain ladder: “Scaling Ladder — 4 sizes, 135M–973M, 200 TPP” Collection by jkminder Sep 3 - jkminder/d12_optimized_286m_seed1 Text Generation • 0.3B • Updated Sep 3 • 40 • 1 jkminder/d12_optimized_286m_seed2 Text Generation • 0.3B • Updated Sep 3 • 1.49k jkminder/d12_optimized_286m_seed3 Text Generation • 0.3B • Updated Sep 3 • 1.48k jkminder/d12_optimized_286m_seed4 Text Generation • 0.3B • Updated Sep 3 • 17
LOCALS Collection by xnxnxnnxnxnxnnx9897867564x6x 13 days ago - openai-community/gpt2 Text Generation • 0.1B • Updated Feb 19, 2024 • 31.3M • 3.92k superwhisper/s1-mini Text Generation • 0.8B • Updated Aug 28 • 1.92k • 385 Nanbeige/Nanbeige4.2-3B-DSpark Text Generation • 0.8B • Updated Aug 31 • 445 • 29 Qwen/Qwen3-0.6B Text Generation • 0.8B • Updated Jul 26, 2025 • 21.4M • • 1.88k
Quantized Models Collection by systalyze Sep 3 - systalyze/gemma-4-26B-A4B-it-ExpertsINT4-FP8 Image-Text-to-Text • 26B • Updated Sep 4 • 303 • 2
Huihui Collection by dzenatoriusz Sep 3 - huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF Image-Text-to-Text • 27B • Updated 28 days ago • 3.83M • 1.8k
huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF Image-Text-to-Text • 27B • Updated 28 days ago • 3.83M • 1.8k
1pp One Persona Pretraining: 3 sizes × 3 pretraining conditions, base and SFT models Collection by Raghav-Singhal 1 day ago - Raghav-Singhal/1pp-1b-asst-base Text Generation • 1.0B • Updated Sep 4 • 16 Raghav-Singhal/1pp-0.5b-asst-base Text Generation • 0.6B • Updated Sep 4 • 17 Raghav-Singhal/1pp-0.5b-asst-sft Text Generation • 0.6B • Updated Sep 3 • 14 Raghav-Singhal/1pp-0.5b-raw-base Text Generation • 0.6B • Updated Sep 4 • 16
To Try Later (3080 - 10GB) Collection by pkarath 2 days ago - XHToken/Spark-X2.5-4B Text Generation • 4B • Updated Sep 15 • 29.2k • 1.44k IFM/K2-Horizon-7B Text Generation • 9B • Updated 3 days ago • 84.4k • • 282 unsloth/Qwen3.5-9B-GGUF Image-Text-to-Text • 9B • Updated Mar 2 • 1.77M • 1.06k ornith-ai/Ornith-1.0-9B-GGUF Text Generation • 9B • Updated Jun 25 • 2.4M • 699
technical slang translation - dataset review Collection by nikavetshtein Sep 8 - cais/mmlu Viewer • Updated Mar 8, 2024 • 231k • 574k • 884 TIGER-Lab/MMLU-Pro Benchmark • Updated May 2 • 12.1k • 396k • 601 deepset/prompt-injections Viewer • Updated Jul 30, 2024 • 662 • 16.4k • 200 McGill-NLP/speech-translation-and-summarization Viewer • Updated Aug 12 • 10k • 517 • 6
Scaling Ladder (optimized) — 3 sizes, 286M–897M, 200 TPP Speedrun architecture: 8 pretraining seeds/size, anneal marks every 10 TPP as revisions. Plain ladder: “Scaling Ladder — 4 sizes, 135M–973M, 200 TPP” Collection by jkminder Sep 3 - jkminder/d12_optimized_286m_seed1 Text Generation • 0.3B • Updated Sep 3 • 40 • 1 jkminder/d12_optimized_286m_seed2 Text Generation • 0.3B • Updated Sep 3 • 1.49k jkminder/d12_optimized_286m_seed3 Text Generation • 0.3B • Updated Sep 3 • 1.48k jkminder/d12_optimized_286m_seed4 Text Generation • 0.3B • Updated Sep 3 • 17
first collection Collection by SumeroStudio Sep 3 - Running Agents Featured 1.2k Qwen3 Coder WebDev 🌍 1.2k Generate web page code from a description Running Featured 247 Gemma 4 WebGPU 🚀 247 Run Gemma 4 locally in-browser on WebGPU w/ Transformers.js Running Agents 77 Medical Diagnosis 📉 77 Classify symptoms into possible medical conditions Running on Zero Agents Featured 181 MarioGPT 🦀 181 Generate a playable Mario level from a text prompt
Running Featured 247 Gemma 4 WebGPU 🚀 247 Run Gemma 4 locally in-browser on WebGPU w/ Transformers.js
Running on Zero Agents Featured 181 MarioGPT 🦀 181 Generate a playable Mario level from a text prompt
13 days ago 
