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.
SmolLM-1.7B-Instruct-quantized.w4a16Qwen2.5-1.5B-quantized.w8a8glove-6B-quantizedMeta-Llama-3.1-8B-Instruct-quantized.w4a16Qwen2.5-VL-3B-Instruct-quantized.w8a8Qwen2.5-VL-7B-Instruct-quantized.w8a8granite-3.1-2b-instruct-quantized.w4a16Meta-Llama-3.1-8B-Instruct-quantized.w8a8mlx-FLUX.1-schnell-4bit-quantizedLlama-4-Scout-17B-16E-Instruct-quantized.w4a16Meta-Llama-3.1-70B-Instruct-quantized.w4a16Llama-3.2-1B-Instruct-quantized.w8a8Llama-3.3-70B-Instruct-quantized.w4a16Meta-Llama-3.1-8B-quantized.w8a8phi-4-quantized.w8a8Mistral-Small-24B-Instruct-2501-quantized.w8a8AnimeGen-I2V-QuantizedQwen2.5-0.5B-quantized.w8a16WeMM-Embedding-2B-QuantizedMiniCPM5-2B-RotSVDMix-QuantizedMistral-Small-3.1-24B-Instruct-2503-quantized.w4a16whisper-large-v3-turbo-quantized.w4a16Llama-4-Maverick-17B-128E-Instruct-quantized.w4a16granite-3.1-8b-instruct-quantized.w4a16whisper-small-quantized.w8a8Qwen2.5-VL-72B-Instruct-quantized.w4a16Qwen2.5-VL-7B-Instruct-quantized.w4a16Mistral-Nemo-Instruct-2407-quantized.w4a16Qwen2.5-7B-Instruct-quantized.w8a8Meta-Llama-3-8B-Instruct-quantized.w8a8