STT Collection by MestrePetrus about 4 hours ago - nvidia/parakeet-tdt-0.6b-v3 Automatic Speech Recognition • 0.6B • Updated Aug 5 • 540k • 1.27k moondream/parakeet-redux Automatic Speech Recognition • 0.1B • Updated Sep 23 • 10.1k • 313
Qwen 3.8 2B MLX Quantisations for Qwen 3.8 2B Collection by SiddhJagani Aug 19 - SiddhJagani/Qwen3.8-2B-mlx-fp16 Text Generation • 2B • Updated Aug 20 • 59 SiddhJagani/Qwen3.8-2B-mlx-8Bit Text Generation • 2B • Updated Aug 20 • 65 SiddhJagani/Qwen3.8-2B-mlx-6Bit Text Generation • 2B • Updated Aug 20 • 20 SiddhJagani/Qwen3.8-2B-mlx-5Bit Text Generation • 2B • Updated Aug 20 • 24
Qwen 3.8 4B MLX Quantisations for Qwen 3.8 4B Collection by SiddhJagani Aug 19 - SiddhJagani/Qwen3.8-4B-mlx-fp16 Text Generation • 4B • Updated Aug 20 • 36 SiddhJagani/Qwen3.8-4B-mlx-8Bit Text Generation • 4B • Updated Aug 20 • 94 SiddhJagani/Qwen3.8-4B-mlx-6Bit Text Generation • 4B • Updated Aug 20 • 128 SiddhJagani/Qwen3.8-4B-mlx-5Bit Text Generation • 4B • Updated Aug 20 • 26
Qwen 3.8 9B MLX Quantisations for Qwen 3.8 9B Collection by SiddhJagani Aug 19 - SiddhJagani/Qwen3.8-9B-mlx-fp16 Text Generation • 9B • Updated Aug 19 • 158 SiddhJagani/Qwen3.8-9B-mlx-8Bit Text Generation • 9B • Updated Aug 19 • 562 • 1 SiddhJagani/Qwen3.8-9B-mlx-6Bit Text Generation • 9B • Updated Aug 19 • 164 SiddhJagani/Qwen3.8-9B-mlx-5Bit Text Generation • 9B • Updated Aug 19 • 114
MatMasterBench MatMasterBench is a broad-and-deep benchmark system organized around materials research capabilities. Collection by MatMaster-DP Aug 19 1 MatMaster-DP/E2EBench-118 Viewer • Updated Aug 18 • 118 • 501 MatMaster-DP/Paper2Arm-5135 Viewer • Updated Aug 17 • 5.14k • 404 • 1 MatMaster-DP/Materials-AutoLab-144 Preview • Updated Aug 17 • 941 MatMaster-DP/MATTER-604 Viewer • Updated Aug 17 • 604 • 61
try one day Collection by jugh0 Aug 19 - CompVis/stable-diffusion-v1-4 Text-to-Image • 0.9B • Updated Aug 23, 2023 • 483k • 7.15k
Spicy Collection by Spiderssh Aug 19 - huihui-ai/Huihui-CyberStrike-OffSec-35B-abliterated Text Generation • 36B • Updated Aug 11 • 1.03k • • 114
huihui-ai/Huihui-CyberStrike-OffSec-35B-abliterated Text Generation • 36B • Updated Aug 11 • 1.03k • • 114
Gradient-Faithful Surrogates paper models Final checkpoints of Llama3 and Qwen3 models from Gradient-Faithful Surrogates for KV-Cache Quantization Recovery paper Collection by brain-lab Aug 19 - brain-lab/kivi-llama-gradient-faithful 8B • Updated Aug 19 • 12 brain-lab/qjl-llama-gradient-faithful 8B • Updated Aug 19 • 10 brain-lab/kivi-qwen3-gradient-faithful 4B • Updated Aug 19 • 12 brain-lab/qjl-qwen3-gradient-faithful 4B • Updated Aug 19 • 10
Local host AI Collection by yongzs1218 Aug 19 - syedghaziraza/mistral-7b-finetuned-gguf 7B • Updated Aug 10 • 7 • 1 hfl/llama-3-chinese-8b-instruct-v3 Text Generation • 8B • Updated Jul 11, 2025 • 9.04k • • 66
Unsonsored Collection by ayoub-gouahi Aug 19 - orcarouter/Qwen3.8-27B-Uncensored-GGUF Image-Text-to-Text • 27B • Updated 14 days ago • 98.5k • 1.75k
orcarouter/Qwen3.8-27B-Uncensored-GGUF Image-Text-to-Text • 27B • Updated 14 days ago • 98.5k • 1.75k
STT Collection by MestrePetrus about 4 hours ago - nvidia/parakeet-tdt-0.6b-v3 Automatic Speech Recognition • 0.6B • Updated Aug 5 • 540k • 1.27k moondream/parakeet-redux Automatic Speech Recognition • 0.1B • Updated Sep 23 • 10.1k • 313
try one day Collection by jugh0 Aug 19 - CompVis/stable-diffusion-v1-4 Text-to-Image • 0.9B • Updated Aug 23, 2023 • 483k • 7.15k
Qwen 3.8 2B MLX Quantisations for Qwen 3.8 2B Collection by SiddhJagani Aug 19 - SiddhJagani/Qwen3.8-2B-mlx-fp16 Text Generation • 2B • Updated Aug 20 • 59 SiddhJagani/Qwen3.8-2B-mlx-8Bit Text Generation • 2B • Updated Aug 20 • 65 SiddhJagani/Qwen3.8-2B-mlx-6Bit Text Generation • 2B • Updated Aug 20 • 20 SiddhJagani/Qwen3.8-2B-mlx-5Bit Text Generation • 2B • Updated Aug 20 • 24
Spicy Collection by Spiderssh Aug 19 - huihui-ai/Huihui-CyberStrike-OffSec-35B-abliterated Text Generation • 36B • Updated Aug 11 • 1.03k • • 114
huihui-ai/Huihui-CyberStrike-OffSec-35B-abliterated Text Generation • 36B • Updated Aug 11 • 1.03k • • 114
Qwen 3.8 4B MLX Quantisations for Qwen 3.8 4B Collection by SiddhJagani Aug 19 - SiddhJagani/Qwen3.8-4B-mlx-fp16 Text Generation • 4B • Updated Aug 20 • 36 SiddhJagani/Qwen3.8-4B-mlx-8Bit Text Generation • 4B • Updated Aug 20 • 94 SiddhJagani/Qwen3.8-4B-mlx-6Bit Text Generation • 4B • Updated Aug 20 • 128 SiddhJagani/Qwen3.8-4B-mlx-5Bit Text Generation • 4B • Updated Aug 20 • 26
Gradient-Faithful Surrogates paper models Final checkpoints of Llama3 and Qwen3 models from Gradient-Faithful Surrogates for KV-Cache Quantization Recovery paper Collection by brain-lab Aug 19 - brain-lab/kivi-llama-gradient-faithful 8B • Updated Aug 19 • 12 brain-lab/qjl-llama-gradient-faithful 8B • Updated Aug 19 • 10 brain-lab/kivi-qwen3-gradient-faithful 4B • Updated Aug 19 • 12 brain-lab/qjl-qwen3-gradient-faithful 4B • Updated Aug 19 • 10
Qwen 3.8 9B MLX Quantisations for Qwen 3.8 9B Collection by SiddhJagani Aug 19 - SiddhJagani/Qwen3.8-9B-mlx-fp16 Text Generation • 9B • Updated Aug 19 • 158 SiddhJagani/Qwen3.8-9B-mlx-8Bit Text Generation • 9B • Updated Aug 19 • 562 • 1 SiddhJagani/Qwen3.8-9B-mlx-6Bit Text Generation • 9B • Updated Aug 19 • 164 SiddhJagani/Qwen3.8-9B-mlx-5Bit Text Generation • 9B • Updated Aug 19 • 114
Local host AI Collection by yongzs1218 Aug 19 - syedghaziraza/mistral-7b-finetuned-gguf 7B • Updated Aug 10 • 7 • 1 hfl/llama-3-chinese-8b-instruct-v3 Text Generation • 8B • Updated Jul 11, 2025 • 9.04k • • 66
MatMasterBench MatMasterBench is a broad-and-deep benchmark system organized around materials research capabilities. Collection by MatMaster-DP Aug 19 1 MatMaster-DP/E2EBench-118 Viewer • Updated Aug 18 • 118 • 501 MatMaster-DP/Paper2Arm-5135 Viewer • Updated Aug 17 • 5.14k • 404 • 1 MatMaster-DP/Materials-AutoLab-144 Preview • Updated Aug 17 • 941 MatMaster-DP/MATTER-604 Viewer • Updated Aug 17 • 604 • 61
Unsonsored Collection by ayoub-gouahi Aug 19 - orcarouter/Qwen3.8-27B-Uncensored-GGUF Image-Text-to-Text • 27B • Updated 14 days ago • 98.5k • 1.75k
orcarouter/Qwen3.8-27B-Uncensored-GGUF Image-Text-to-Text • 27B • Updated 14 days ago • 98.5k • 1.75k
about 4 hours ago 
