GGUF models by grapevine-AI
77 GGUF models quantized by grapevine-AI on Hugging Face. Sizes run from 494M to 111B parameters. The longest trained context is 10240K tokens.
About grapevine-AI on Hugging Face
grapevine-AI has published 77 GGUF models that ggufmodels.com tracks, across families such as Qwen, Llama and Gemma. The most downloaded are calm3-22b-chat, Gemma 2 27b It and Mistral Nemo Instruct 2407.
The quants grapevine-AI publishes most often are Q4_K_M (77), BF16 (65), IQ4_XS (51) and Q5_K_M (37). Their Q4_K_M files range from 0.4 to 67.1 GB. Parameter counts run from 494M to 111B, and the longest trained context window is 10240K tokens.
Frequently asked questions
What GGUF models has grapevine-AI published?
77 models are listed here, mainly from the Qwen, Llama and Gemma families. The most downloaded is calm3-22b-chat.
Which quants does grapevine-AI publish?
The most common are Q4_K_M (77 models), BF16 (65 models), IQ4_XS (51 models) and Q5_K_M (37 models).