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-Nano-4B-BF16NVIDIA-Nemotron-3-Super-120B-A12B-BF16NVIDIA-Nemotron-3-Nano-30B-A3B-BF16Nemotron-3-Embed-1B-BF16NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16Qwen3.8-27B-NVFP4-BF16-LMHeadQwen3.6-27B-PrismaSCOUT-Blackwell-NVFP4-BF16-vllmNemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16moshiko-pytorch-bf16NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16Nemotron-3-Embed-8B-BF16gpt-oss-20b-BF16gpt-oss-120b-bf16gpt-oss-20b-bf16Kokoro-82M-bf16Ministral-3-14B-Instruct-2512-BF16Ministral-3-3B-Instruct-2512-BF16Qwen3.8-27B-BF16-INT4-W4A16-G32-AutoRoundNVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16Qwen3.8-27B-GPTQ-Int4-sym-G128-MTP-BF16command-a-plus-05-2026-bf16Ministral-3-8B-Instruct-2512-BF16Qwen3.8-27B-AWQ-BF16-INT4gemma-3n-E4B-it-MLX-bf16EAGLE3-gpt-oss-120b-bf16gpt-oss-bf16NVIDIA-Nemotron-Nano-12B-v2-VL-BF16Qwen3-1.7B-MLX-bf16nomicai-modernbert-embed-base-bf16
