GGUF models by Aashraf995
37 GGUF models quantized by Aashraf995 on Hugging Face. Sizes run from 494M to 14.8B parameters. The longest trained context is 1024K tokens.
About Aashraf995 on Hugging Face
Aashraf995 has published 37 GGUF models that ggufmodels.com tracks, across families such as Qwen, Gemma and Opencoder. The most downloaded are KaLM Embedding Multilingual Mini Instruct v2.5, CodeQwen1.5 7B Chat and Codegemma 7b.
The quants Aashraf995 publishes most often are Q4_K_M (16), Q8_0 (15), Q6_K (4) and Q5_K_S (1). Their Q4_K_M files range from 1.1 to 9.0 GB. Parameter counts run from 494M to 14.8B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has Aashraf995 published?
37 models are listed here, mainly from the Qwen, Gemma and Opencoder families. The most downloaded is KaLM Embedding Multilingual Mini Instruct v2.5.
Which quants does Aashraf995 publish?
The most common are Q4_K_M (16 models), Q8_0 (15 models), Q6_K (4 models) and Q5_K_S (1 models).