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.
Meta-Llama-3.1-8B-Instruct-quantized.w4a16Meta-Llama-3.1-8B-Instruct-quantized.w8a8Llama-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.w8a8Mistral-Small-24B-Instruct-2501-quantized.w8a8Mistral-Small-3.1-24B-Instruct-2503-quantized.w4a16Llama-4-Maverick-17B-128E-Instruct-quantized.w4a16Qwen2.5-7B-Instruct-quantized.w8a8Mistral-Small-3.1-24B-Instruct-2503-quantized.w8a8Llama-3.3-70B-Instruct-quantized.w8a8Meta-Llama-3.1-8B-Instruct-quantized.w8a16Mistral-Small-24B-Instruct-2501-quantized.w4a16Meta-Llama-3.1-70B-Instruct-quantized.w8a8Llama-3.2-3B-Instruct-quantized.w8a8Meta-Llama-3.1-405B-Instruct-quantized.w4a16Pixtral-Large-Instruct-2411-hf-quantized.w4a16multilingual-e5-large-quantizedQwen2.5-7B-Instruct-quantized.w4a16NVIDIA-Nemotron-Nano-9B-v2-quantized.w4a16Llama-3.2-3B-Instruct-quantized.w8a8multilingual-e5-base-similarity-v1-onnx-quantizedMeta-Llama-3.1-405B-Instruct-quantized.w8a16multilingual-e5-base-v3-onnx-quantizedopenHermes_mistral_eugenio_7b-quantized-ggufMeta-Llama-3.1-8B-quantized.w8a16madlad400-3b-mt-optimized-quantized-onnxMeta-Llama-3.1-70B-Instruct-quantized.w8a16