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-FP8Qwen3.8-27B-FP8Qwen3.6-27B-FP8Qwen3-VL-8B-Instruct-FP8Qwen3.5-35B-A3B-FP8Qwen3-Coder-Next-FP8Qwen3-Coder-30B-A3B-Instruct-FP8Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8gemma-4-26B-A4B-it-FP8-dynamicGLM-5.2-FP8Qwen3-4B-Instruct-2507-FP8Qwen3.5-122B-A10B-FP8Qwen3-Coder-480B-A35B-Instruct-FP8Qwen3-8B-FP8Qwen3.5-397B-A17B-FP8WanVideo_comfy_fp8_scaledLTX-2.3-fp8Qwen3.8-Flash-Next-FP8Qwen3-VL-Embedding-8B-FP8Ornith-1.5-35B-A3B-FP8Qwen3-30B-A3B-Instruct-2507-FP8Llama-3.1-405B-FP8Ornith-1.0-35B-FP8Ornith-1.0-35B-FP8NVIDIA-Nemotron-3-Nano-30B-A3B-FP8Qwen3-235B-A22B-Instruct-2507-FP8NVIDIA-Nemotron-3.5-Lightning-30B-A3B-FP8Qwen3-VL-4B-Instruct-FP8Ornith-1.5-397B-FP8Ornith-1.0-397B-FP8
