models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-FP8Llama-3.2-3B-Instruct-FP8-dynamicLlama-3.2-1B-Instruct-FP8-dynamicQwen3-32B-NVFP4Qwen3-Coder-Next-FP8-dynamicQwen2.5-1.5B-quantized.w8a8Llama-3.2-3B-Instruct-FP8Meta-Llama-3.1-70B-Instruct-FP8DeepSeek-Coder-V2-Lite-Instruct-FP8Meta-Llama-3.1-8B-Instruct-FP8Llama-3.3-70B-Instruct-FP8-dynamicphi-4-FP8-dynamicLlama-3.2-1B-Instruct-FP8granite-3.1-2b-instruct-quantized.w4a16Qwen3-Coder-Next-NVFP4Meta-Llama-3.1-8B-Instruct-quantized.w4a16Qwen3-VL-235B-A22B-Instruct-FP8-dynamicMinistral-3-14B-Instruct-2512-FP8-dynamicQwen3-8B-speculator.eagle3Llama-3.3-70B-Instruct-NVFP4Meta-Llama-3.1-8B-Instruct-FP8-dynamicQwen3-8B-quantized.w4a16DeepSeek-R1-Distill-Qwen-32B-quantized.w4a16Qwen3-0.6B-quantized.w4a16gemma-2-9b-it-FP8Meta-Llama-3.1-8B-Instruct-quantized.w8a8Llama-3.1-8B-Instruct-speculator.eagle3DeepSeek-R1-Distill-Llama-70B-FP8-dynamicQwen3-VL-235B-A22B-Instruct-NVFP4Qwen3-14B-NVFP4