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-INT8Phi-4-mini-instruct-INT8-INT4Qwen3-4B-INT8-INT4GLM-5.2-Int4-Int8MixQwen2.5-7B-Instruct-GPTQ-Int8Qwen2.5-32B-Instruct-GPTQ-Int8Qwen2.5-3B-Instruct-GPTQ-Int8Qwen2.5-14B-Instruct-GPTQ-Int8GLM-5.3-Int4-Int8Mixtiny-qwen3-moe-w8a8-int8Qwen2.5-72B-Instruct-GPTQ-Int8Qwen3-8B-GPTQ-Int8Qwen3-Embedding-0.6B-int8-ovSpark-X2.5-4B-INT8Qwen2.5-Coder-32B-Instruct-GPTQ-Int8Qwen2.5-Coder-7B-Instruct-GPTQ-Int8qwen3.8-flash-coder-44gb-selective-int8DeepSeek-R1-Block-INT8GLM-5.3-DERISKED-Int4-Int8MixQwen3-0.6B-GPTQ-Int8Qwen3-1.7B-GPTQ-Int8opt-125m-int8wo-partial-quantQwen1.5-MoE-A2.7B-Chat-w-int8-a-int8-symTinyLlama-1.1B-Chat-v1.0-int8-ovQwen2.5-1.5B-Instruct-GPTQ-Int8DeepSeek-OCR-2-GPTQ-INT8Qwen2.5-0.5B-Instruct-GPTQ-Int8Qwen2.5-Coder-14B-Instruct-GPTQ-Int8Qwen2-72B-Instruct-GPTQ-Int8