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.
Qwen3.6-27B-INT8-W8A8Qwen3.6-35B-A3B-INT8-W8A8qwen3.8-flash-coder-44gb-selective-int8GLM-5.3-DERISKED-Int4-Int8MixDeepSeek-OCR-2-GPTQ-INT8LFM2.5-350M-int8-ovPhi-4-mini-instruct-int8-ovQwen-1_8B-Chat-Int8Qwen-7B-Chat-Int8Qwen-14B-Chat-Int8Qwen-72B-Chat-Int8Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16LFM2.5-1.2B-Thinking-ToMoE-INT8Qwen3-Embedding-0.6B-ONNX-INT8Nanbeige4.2-3B-GPTQ-Int8Qwen3-Omni-30B-A3B-Thinking-INT8FP16Qwen3.5-4B-Uncensored-HauhauCS-Aggressive_INT8-convrotmoss-moon-003-sft-int8GLM-5.2-Int4-MSE-Int8MixLFM2.5-2.6B-heretic-int8-ovLFM2.5-350M-ToMoE-INT8ark-asr-0.6b-int8-onnxSeed-OSS-36B-Instruct-GPTQ-Int8internlm3-8b-instruct-smoothquant-int8LFM2.5-2.6B-openvino-int8-npuJoyAI-LLM-Flash-INT8moss-moon-003-sft-plugin-int8GLM-5.2-Int8Mix-NVFP4GLM-4.6-INT8DeepSeek-R1-0528-Qwen3-8B-Int8-W8A16
