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-Coder-30B-A3B-Instruct-GPTQ-Int8Llama-Guard-3-8B-INT8Meta-Llama-3.1-8B-Instruct-int8qwen3.8-flash-coder-44gb-selective-int8GLM-5.2-colibri-int4-g64-with-int8-mtpQwen2.5-32B-Instruct-GPTQ-Int8Qwen2.5-7B-Instruct-GPTQ-Int8Qwen2.5-3B-Instruct-GPTQ-Int8Qwen2.5-14B-Instruct-GPTQ-Int8tiny-qwen3-moe-w8a8-int8GLM-5.2-Int4-Int8MixQwen3-4B-INT8-ConvRot-ComfyUIGLM-5.3-Int4-Int8MixQwen3-4B-Instruct-2507-GPTQ-Int8Phi-4-mini-instruct-INT8-INT4Qwen3-Embedding-0.6B-int8-ovQwen3-4B-INT8-INT4Qwen3.6-35B-A3B-INT8-W8A8DeepSeek-OCR-2-GPTQ-INT8Spark-X2.5-4B-INT8Qwen3.8-27B-W8A8-INT8GLM-5.3-DERISKED-Int4-Int8MixQwen2.5-Coder-7B-Instruct-GPTQ-Int8Qwen3-0.6B-GPTQ-Int8GLM-5.2-colibri-E8-IQ3-with-int8-mtptinyllama-1-1b-chat-onnx-genai-int4-kquantlast-emb-int8-vivo-x300tinyllama-1-1b-chat-onnx-genai-int4-kquantlast-emb-int8-graviton-g4Qwen2.5-72B-Instruct-GPTQ-Int8Qwen2.5-Coder-32B-Instruct-GPTQ-Int8DeepSeek-R1-Block-INT8