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.
Qwen3.8-27B-INT8-W8A8Mistral-Small-24B-Instruct-2501-quantized.w8a8Mistral-Small-3.1-24B-Instruct-2503-quantized.w8a8Qwen3.6-27B-INT8-W8A8Qwen3.6-35B-A3B-INT8-W8A8Qwen2.5-7B-Instruct-quantized.w8a8Ornith-1.5-35B-A3B-abliterated-W8A8Qwen2.5-7B-Instruct-FP8-W8A8Qwen3-1.7B-W8A8Qwen3-VL-2B-Instruct-SmoothQuant-W8A8-FP8LongCat-Next-w8a8-int8-GB10Atria-Dawn-Preview-Ascend-w8a8Qwen3.5-27B-W8A8qwen36-27b-ft-grm-w8a8GLM-4.6-quantized.w8a8Qwen3-VL-4B-Instruct-SmoothQuant-W8A8-FP8Qwen3.5-0.8B-W8A8MiniCPM5-2B-W8A8-arm-FlagOSPixtral-Large-Instruct-2411-hf-quantized.w8a8Qwen3-VL-8B-Instruct-SmoothQuant-W8A8-FP8qwen3-14b-meow-gptq-w8a8GLM-4.6V-Flash-W8A8-INT8InternLM2-1.8B-w8a8-RKLLM-v1.2.3Qwen3-8B-W8A8Qwen3-8B-W8A8Ministral-8B-Instruct-2410-W8A8shisa-v2-llama3.1-405b-W8A8-INT8DeepSeek-R1-Distill-Qwen-7B-GPTQ_W8A8_G128Qwen3-4B-Instruct-2507_w8a8_g128_1.2.2_rkllmdeepseek-R1-bf16-w8a8
