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-dynamicQwen3-Coder-Next-FP8-dynamicLlama-3.3-70B-Instruct-FP8-dynamicphi-4-FP8-dynamicDeepSeek-R1-Distill-Qwen-32B-FP8-dynamicQwen3-VL-235B-A22B-Instruct-FP8-dynamicMinistral-3-14B-Instruct-2512-FP8-dynamicMeta-Llama-3.1-8B-Instruct-FP8-dynamicDeepSeek-R1-Distill-Llama-70B-FP8-dynamicBielik-11B-v3.0-Instruct-FP8-DynamicQwen3-30B-A3B-FP8-DynamicMistral-Small-24B-Instruct-2501-FP8-dynamicQwen2.5-7B-Instruct-FP8-dynamicMeta-Llama-3.1-8B-Instruct-FP8-dynamicQwen3-8B-FP8-dynamictinyllama-oneshot-w8a8-channel-dynamic-token-v2Qwen3-Coder-Next-FP8-DynamicQwen3-Reranker-4B-FP8-Dynamictinyllama-oneshot-w8a8-dynamic-token-v2medgemma-27b-it-FP8-DynamicMeta-Llama-3.1-405B-Instruct-FP8-dynamicNVIDIA-Nemotron-3-Ultra-550B-A55B-FP8-dynamicKimi-K3-Alis-MLX-Dynamic-2.10bpwQwen3-32B-FP8-dynamicKimi-K2.7-Code-Alis-MLX-Dynamic-3.6bpwQwen3-VL-32B-Instruct-FP8-dynamicNVIDIA-Nemotron-Nano-9B-v2-FP8-dynamicQwen3.8-27B-Heretic-Dynamic-GGUFDeepSeek-R1-Distill-Qwen-1.5B-FP8-Dynamic