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.
Mixtral-8x7B-v0.1-GPTQc4ai-command-r-plus-GPTQMeta-Llama-3.1-8B-Instruct-GPTQ-INT4EuroLLM-22B-Instruct-GPTQMixtral-8x7B-Instruct-v0.1-GPTQPhi-4-mini-instruct-GPTQ-8bitHY-MT1.5-1.8B-GPTQ-Int4Meta-Llama-3.1-405B-Instruct-GPTQ-INT4Meta-Llama-3.1-70B-Instruct-GPTQ-INT4granite-4.2-8b-2bit-gptq-mlxLlama-3.1-8B-Instruct-GPTQ-Int8Mistral-Small-24B-Instruct-2501-GPTQ-INT4Llama-3.2-1B-Instruct-gptqmodel-4bit-vortex-v1HY-MT1.5-7B-GPTQ-Int4Meta-Llama-3.1-8B-Instruct-GPTQ-Q_8Llama-3.2-1B-GPTQEXAONE-4.0-32B-GPTQLlama-3.2-1B-Instruct-gptqmodel-4bit-vortex-v2.5granite-4.2-8b-4bit-gptq-mlxAgents-A1-GPTQ-INT4-Symsalamandra-7b-instruct-gptqgranite-4.2-3b-8bit-gptq-mlxEXAONE-4.0-1.2B-GPTQ-Int8granite-4.2-3b-2bit-gptq-mlxFalcon-180B-Chat-GPTQgranite-4.2-8b-8bit-gptq-mlxQwopus3.6-27B-Coder-GPTQ-Prometa-llama_Llama-3.2-1B-Instruct-auto_gptq-int4-gs128-symSauerkrautLM-Mixtral-8x7B-Instruct-GPTQLlama-3.2-1B-Instruct-GPTQ-Int4