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.
Mistral-Nemo-Instruct-2407-W8A8-Dynamic-Per-TokenQwen2.5-1.5B-quantized.w8a8Qwen3-30B-A3B.w8a8Qwen3.8-27B-SmoothQuant-W8A8-INT8Llama-3.2-1B-quantized.w8a8Qwen2.5-VL-3B-Instruct-quantized.w8a8Llama-3.2-3B-quantized.w8a8Qwen3-VL-8B-Instruct-w8a8-llmcompressorQwen2.5-VL-7B-Instruct-quantized.w8a8Meta-Llama-3.1-8B-Instruct-quantized.w8a8Qwen3.8-27B-INT8-W8A8Llama-3.2-1B-Instruct-quantized.w8a8Qwen3.5-4B-quantized.w8a8Meta-Llama-3.1-8B-quantized.w8a8Qwen3-30B-A3B-Instruct-2507-quantized.w8a8Qwen3.5-9B-quantized.w8a8Mistral-Small-24B-Instruct-2501-quantized.w8a8phi-4-quantized.w8a8NuExtract3-W8A8whisper-large-v3-quantized.w8a8whisper-large-v3-turbo-quantized.w8a8tinyllama-oneshot-w8a8-channel-dynamic-token-v2tinyllama-oneshot-w8a8-dynamic-token-v2Qwen3-8B.w8a8tiny-qwen3-moe-w8a8-int8tinyllama-w8a8-compressedMistral-Small-3.1-24B-Instruct-2503-quantized.w8a8Phi-4-mini-instruct-quantized.w8a8Qwen3-Coder-30B-A3B-Instruct-W8A8Qwen3.8-27B-INT8-W8A8-imatrix-MTP