GGUF models by yasserrmd
54 GGUF models quantized by yasserrmd on Hugging Face. Sizes run from 354M to 14.7B parameters. The longest trained context is 986K tokens.
About yasserrmd on Hugging Face
yasserrmd has published 54 GGUF models that ggufmodels.com tracks, across families such as Qwen, Seed and Lfm. The most downloaded are Coder GRPO 3B, DeepSeek R1 Distill Qwen 1.5B and deepseek esg assistant.
The quants yasserrmd publishes most often are Q2_K (53), Q4_K_M (52), Q8_0 (51) and Q5_K_M (51). Their Q4_K_M files range from 0.2 to 8.9 GB. Parameter counts run from 354M to 14.7B, and the longest trained context window is 986K tokens.
Frequently asked questions
What GGUF models has yasserrmd published?
54 models are listed here, mainly from the Qwen, Seed and Lfm families. The most downloaded is Coder GRPO 3B.
Which quants does yasserrmd publish?
The most common are Q2_K (53 models), Q4_K_M (52 models), Q8_0 (51 models) and Q5_K_M (51 models).