GGUF models by llmware
118 GGUF models quantized by llmware on Hugging Face. Sizes run from 494M to 119B parameters. The longest trained context is 1024K tokens.
About llmware on Hugging Face
llmware has published 118 GGUF models that ggufmodels.com tracks, across families such as Qwen, Slim and Phi. The most downloaded are dragon mistral 7b v0, slim summary phi 3 and slim summary tool.
The quants llmware publishes most often are Q4_K_M (64), Q4_0 (2), Q8_0 (1) and Q4_1 (1). Their Q4_K_M files range from 0.4 to 73.8 GB. Parameter counts run from 494M to 119B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has llmware published?
118 models are listed here, mainly from the Qwen, Slim and Phi families. The most downloaded is dragon mistral 7b v0.
Which quants does llmware publish?
The most common are Q4_K_M (64 models), Q4_0 (2 models), Q8_0 (1 models) and Q4_1 (1 models).