GGUF models by chartreuse-verte
38 GGUF models quantized by chartreuse-verte on Hugging Face. Sizes run from 17M to 30.7B parameters. The longest trained context is 256K tokens.
About chartreuse-verte on Hugging Face
chartreuse-verte has published 38 GGUF models that ggufmodels.com tracks, across families such as Qwen, Ettin and Granite. The most downloaded are Orb Human Typeahead 1b v2.3, Prose Rewriter 4b v1.2 and Orb Human Typeahead 1b v2.2.
The quants chartreuse-verte publishes most often are Q8_0 (38), Q4_K_M (16), Q4_0 (4) and F16 (3). Their Q4_K_M files range from 0.0 to 18.7 GB. Parameter counts run from 17M to 30.7B, and the longest trained context window is 256K tokens.
Frequently asked questions
What GGUF models has chartreuse-verte published?
38 models are listed here, mainly from the Qwen, Ettin and Granite families. The most downloaded is Orb Human Typeahead 1b v2.3.
Which quants does chartreuse-verte publish?
The most common are Q8_0 (38 models), Q4_K_M (16 models), Q4_0 (4 models) and F16 (3 models).