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.
Llama-3.2-3B-Instruct-FP8-dynamicLlama-3.2-1B-Instruct-FP8-dynamicLlama-3.3-70B-Instruct-FP8-dynamicphi-4-FP8-dynamicMeta-Llama-3.1-8B-Instruct-FP8-dynamicQwen2.5-7B-Instruct-FP8-dynamicMistral-Small-24B-Instruct-2501-FP8-dynamicQwen3-8B-FP8-dynamicMeta-Llama-3.1-8B-Instruct-FP8-dynamicBielik-11B-v3.0-Instruct-FP8-DynamicGLM-4.7-Flash-FP8-DynamicMeta-Llama-3.1-405B-Instruct-FP8-dynamicDeepSeek-R1-Distill-Qwen-1.5B-FP8-DynamicLlama-3.3-70B-Instruct-FP8-dynamicNVIDIA-Nemotron-Nano-9B-v2-FP8-dynamicQwen2.5-3B-Instruct-fp8-dynamicSmolLM3-3B-FP8-dynamicBielik-Minitron-7B-v3.0-Instruct-FP8-DynamicQwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-FP8-DynamicQwen2.5-Coder-32B-Instruct-FP8-DynamicQwen2.5-32B-Instruct-fp8-dynamicNVIDIA-Nemotron-3-Ultra-550B-A55B-FP8-dynamicDevstral-Small-2507-FP8-Dynamicgranite-3.1-8b-instruct-FP8-dynamicDeepSeek-R1-0528-Qwen3-8B-FP8-DynamicLlama-3.3-70B-Instruct-FP8-DynamicQwen2.5-Coder-14B-Instruct-FP8-dynamicQwen2.5-3B-FP8-dynamicPhi-4-mini-instruct-FP8-dynamicMeta-Llama-3.1-70B-Instruct-FP8-dynamic