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.
MiniMax-H3-Ref2VA-Turbo-INT8-ConvRotLlama-Guard-3-8B-INT8nllb-200-distilled-600M-ct2-int8distil-whisper-large-v3-int8-ovParakeet-EOU-120M-CoreML-INT8Meta-Llama-3.1-8B-Instruct-int8qwen3.8-flash-coder-44gb-selective-int8bge-small-en-v1.5-int8Qwen3.8-27B-INT8-W8A8Parakeet-TDT-v3-CoreML-INT8-iOS-5sParakeet-TDT-v3-CoreML-INT8Qwen2.5-32B-Instruct-GPTQ-Int8whisper-large-v3-turbo-int8-ovQwen2.5-7B-Instruct-GPTQ-Int8Qwen3.8-27B-Uncensored-INT8FLUX.2-klein-4B-int8-diffusersmadlad400-3b-mt-ct2-int8faster-whisper-large-v3-turbo-int8-ct2Qwen2.5-14B-Instruct-GPTQ-Int8nllb-200-distilled-1.3B-ct2-int8MiniMax-H3-Turbo-INT8-ConvRotOcten-Embedding-4B-INT8Octen-Embedding-8B-INT8nllb-200-distilled-600M-ct2-int8gemma-4-26B-A4B-it-uncensored-heretic-ara-MLX-8bit-int8-affineNemotron-3.5-ASR-Streaming-0.6B-CoreML-INT8Qwen3.8-27B-Uncensored-INT8-W8A16-MTPnllb-200-distilled-1.3B-ct2-int8whisper-base-int8-ovm2m100_418M-ct2-int8