GGUF models by JThomas-CoE
35 GGUF models quantized by JThomas-CoE on Hugging Face. Sizes run from 14.4B to 41B parameters. The longest trained context is 256K tokens.
About JThomas-CoE on Hugging Face
JThomas-CoE has published 35 GGUF models that ggufmodels.com tracks, across families such as Gemma, Qwen and Coe. The most downloaded are CoE-Tiel-Coder-python-n1-55-19B-A3B, coe gemma4 coding hc 14b a4b q4 k m and coe qwen3.6 mmlu pro engineering r25 19b a3b q4 k m.
The quants JThomas-CoE publishes most often are Q4_K_M (33), Q8_0 (1) and Q4_K_XL (1). Their Q4_K_M files range from 10.4 to 26.6 GB. Parameter counts run from 14.4B to 41B, and the longest trained context window is 256K tokens.
Frequently asked questions
What GGUF models has JThomas-CoE published?
35 models are listed here, mainly from the Gemma, Qwen and Coe families. The most downloaded is CoE-Tiel-Coder-python-n1-55-19B-A3B.
Which quants does JThomas-CoE publish?
The most common are Q4_K_M (33 models), Q8_0 (1 models) and Q4_K_XL (1 models).