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-int4-AutoRound-SARLFM2.5-2.6B-AutoRound-W8A16Qwen3.5-397B-A17B-heretic-int4-AutoRoundmistralai_Mistral-7B-Instruct-v0.3-autoround-int4-gs128-symLFM2.5-2.6B-AutoRound-W4A16meta-llama_Llama-3.1-8B-Instruct-auto_round-int4-gs128-asymmeta-llama_Llama-3.1-8B-Instruct-auto_round-int4-gs128-symmeta-llama_Llama-3.2-3B-Instruct-auto_round-int8-gs64-asymmeta-llama_Llama-3.2-3B-Instruct-auto_round-int8-gs64-symmeta-llama_Llama-3.2-1B-Instruct-auto_round-int4-gs128-asymmeta-llama_Llama-3.2-1B-Instruct-auto_round-int4-gs128-symmeta-llama_Llama-3.2-1B-auto_round-int8-gs128-symDevstral-Small-2507-int4-AutoRoundmeta-llama_Llama-3.2-1B-auto_round-int4-gs128-syminternlm_internlm3-8b-instruct-autoround-int8-gs64-symmeta-llama_Llama-3.1-8B-Instruct-auto_round-int8-gs128-asymmistralai_Mistral-Small-24B-Base-2501-autoround-int4-gs128-syminternlm_internlm3-8b-instruct-autoround-int4-gs128-asyminternlm_internlm3-8b-instruct-autoround-int4-gs64-asymtiiuae_Falcon3-3B-Base-autoround-int8-gs128-asymmeta-llama_Llama-3.2-3B-auto_round-int8-gs64-asymmeta-llama_Llama-3.1-8B-auto_round-int4-gs128-asyminternlm_internlm3-8b-instruct-autoround-int4-gs64-syminternlm_internlm3-8b-instruct-autoround-int8-gs64-asymmeta-llama_Llama-3.2-3B-auto_round-int4-gs128-asymmeta-llama_Llama-3.2-3B-Instruct-auto_round-int8-gs128-syminternlm_internlm3-8b-instruct-autoround-int8-gs128-symhappypatrick-Qwen3.5-397B-A17B-heretic-int4-AutoRoundmeta-llama_Llama-3.2-1B-Instruct-auto_round-int8-gs64-asymmeta-llama_Llama-3.2-3B-auto_round-int4-gs64-asym