GGUF models by ermiaazarkhalili
112 GGUF models quantized by ermiaazarkhalili on Hugging Face. Sizes run from 354M to 14.8B parameters. The longest trained context is 256K tokens.
About ermiaazarkhalili on Hugging Face
ermiaazarkhalili has published 112 GGUF models that ggufmodels.com tracks, across families such as Qwen, Lfm and Granite. The most downloaded are Qwen3.8 9B Function Calling xLAM Unsloth, Qwen3.8 4B Function Calling xLAM Unsloth and Qwen3.8 2B Function Calling xLAM Unsloth.
The quants ermiaazarkhalili publishes most often are Q8_0 (112), Q5_K_M (112), Q4_K_M (112) and Q6_K (37). Their Q4_K_M files range from 0.2 to 9.0 GB. Parameter counts run from 354M to 14.8B, and the longest trained context window is 256K tokens.
Frequently asked questions
What GGUF models has ermiaazarkhalili published?
112 models are listed here, mainly from the Qwen, Lfm and Granite families. The most downloaded is Qwen3.8 9B Function Calling xLAM Unsloth.
Which quants does ermiaazarkhalili publish?
The most common are Q8_0 (112 models), Q5_K_M (112 models), Q4_K_M (112 models) and Q6_K (37 models).