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.
Miqu-1-70b-24GB-VRAM-IQ2-XS-SOTANemoTron-SOTA-test-2sot_latn_5mbsot_latn_fullsot_latn_10mblaserxtral-sota-GGUFgemma2-maerak-sotavlad-gpt2-generatorIntel-neural-chat-7b-v3-8-bit-gptqsot_latn_100mbmicrosoft-Orca-2-13b-8-bit-gptqresultsgoogle-gemma-7b-4-bit-gptqmistralai-Mistral-7B-v0.1-4-bit-gptqtiiuae-falcon-40b-instruct-4-bit-gptqberkeley-nest-Starling-LM-7B-alpha-8-bit-gptqlmsys-vicuna-7b-v1.5-4-bit-gptqtiiuae-falcon-40b-instruct-4-bit-bnbgoogle-gemma-7b-8-bit-gptqCOPSD-AfriMGSM-SOT-Qwen3-8Bmeta-llama-Meta-Llama-3-8B-8-bit-gptqmicrosoft-Phi-3-medium-4k-instruct-8-bit-gptqfinal_socratic_dialoGPTIntel-neural-chat-7b-v3-4-bit-gptqlmsys-vicuna-7b-v1.5-8-bit-bnbSmolLM2-135M-Sota-Mix-2048socratic-dialoGPTberkeley-nest-Starling-LM-7B-alpha-4-bit-gptqmicrosoft-Phi-3-medium-4k-instruct-4-bit-gptq01-ai-Yi-1.5-34B-Chat-4-bit-gptq
