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.
Qwen3.6-35B-A3B-NVFP4gemma-4-26B-A4B-it-FP8-dynamicNVIDIA-Nemotron-3.5-Lightning-30B-A3B-FP8Qwen3.8-27B-INT4gemma-3-27b-it-quantized.w4a16Llama-3.2-3B-Instruct-FP8-dynamicgemma-4-12B-it-FP8-Dynamicgemma-4-31B-it-FP8-blockLlama-3.2-1B-Instruct-FP8-dynamicgemma-4-31B-it-FP8-dynamicQwen3-32B-NVFP4Qwen3-Coder-Next-FP8-dynamicQwen3.5-9B-quantized.w4a16Qwen2.5-1.5B-quantized.w8a8Meta-Llama-3.1-70B-Instruct-FP8DeepSeek-Coder-V2-Lite-Instruct-FP8gemma-4-26B-A4B-it-NVFP4Meta-Llama-3.1-8B-Instruct-FP8Llama-3.2-3B-Instruct-FP8Llama-3.3-70B-Instruct-FP8-dynamicphi-4-FP8-dynamicQwen3.5-9B-FP8-dynamicQwen2.5-32B-Instruct-FP8-dynamicLlama-3.2-1B-Instruct-FP8granite-3.1-2b-instruct-quantized.w4a16GLM-5.3-Flash-NVFP4gemma-4-31B-it-NVFP4Qwen3-Coder-Next-NVFP4Muse-Glimmer-30B-FP8-blockMeta-Llama-3.1-8B-Instruct-quantized.w4a16
