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.

Most downloadedNewestLargestLongest contextSmallest
OR
CoE-Tiel-Coder-python-n1-55-19B-A3B
Ornith · JThomas-CoE
Params18.5B
Context256K
Smallest12.5 GB
CodingReasoningTool use
GE
coe gemma4 coding hc 14b a4b q4 k m
Gemma · JThomas-CoE
Params14.4B
Context256K
Q4_K_M10.4 GB
Coding
QW
coe qwen3.6 mmlu pro engineering r25 19b a3b q4 k m
Qwen · JThomas-CoE
Params19.4B
Context256K
Q4_K_M13.2 GB
ReasoningTool use
QW
coe qwen3.6 mmlu pro physics r31 19b a3b q4 k m
Qwen · JThomas-CoE
Params19.4B
Context256K
Q4_K_M13.2 GB
ReasoningTool use
GE
coe gemma4 psychology mmlu pro 14b a4b q4
Gemma · JThomas-CoE
Params14.4B
Context256K
Q4_K_M10.4 GB
GGUF
QW
coe qwen3.5 engineering 18b a3b
Qwen · JThomas-CoE
Params19.8B
Context256K
Q4_K_M13.4 GB
ReasoningTool use
QW
coe qwen3.6 mmlu pro chemistry r31 19b a3b q4 k m
Qwen · JThomas-CoE
Params19.4B
Context256K
Q4_K_M13.2 GB
ReasoningTool use
QW
coe qwen3.6 mmlu pro math r31 19b a3b q4 k m
Qwen · JThomas-CoE
Params19.4B
Context256K
Q4_K_M13.2 GB
ReasoningTool use
GE
coe gemma4 biology mmlu pro 14b a4b q4
Gemma · JThomas-CoE
Params14.4B
Context256K
Q4_K_M10.4 GB
GGUF
QW
coe qwen3.5 math 18b a3b
Qwen · JThomas-CoE
Params19.8B
Context256K
Q4_K_M13.4 GB
ReasoningTool use
QW
coe qwen3.5 coding 18b a3b
Qwen · JThomas-CoE
Params19.8B
Context256K
Q4_K_M13.4 GB
ReasoningTool use
GE
coe gemma4 chemistry mmlu pro 14b a4b q4
Gemma · JThomas-CoE
Params14.4B
Context256K
Q4_K_M10.4 GB
GGUF
QW
coe qwen3.5 web 18b a3b
Qwen · JThomas-CoE
Params19.8B
Context256K
Q4_K_M13.4 GB
ReasoningTool use
GE
coe gemma4 physics hc 14b a4b q4 k m
Gemma · JThomas-CoE
Params14.4B
Context256K
Q4_K_M10.4 GB
GGUF
QW
coe qwen3.5 biology 18b a3b
Qwen · JThomas-CoE
Params19.8B
Context256K
Q4_K_M13.4 GB
ReasoningTool use
QW
coe qwen3.6 hc coding web r25 19b a3b q4 k m
Qwen · JThomas-CoE
Params19.4B
Context256K
Q4_K_M13.2 GB
ReasoningTool use
CO
CoE python2 40b A3b
Coe · JThomas-CoE
Params41B
Context256K
Q4_K_M26.6 GB
CodingTool use
GE
coe gemma4 physics mmlu pro 14b a4b q4
Gemma · JThomas-CoE
Params14.4B
Context256K
Q4_K_M10.4 GB
GGUF
QW
coe qwen3.5 vocational 18b a3b
Qwen · JThomas-CoE
Params19.8B
Context256K
Q4_K_M13.4 GB
ReasoningTool use
QW
coe qwen3.6 hc coding python r25 19b a3b q4 k m
Qwen · JThomas-CoE
Params19.4B
Context256K
Q4_K_M13.2 GB
CodingReasoningTool use
QW
coe qwen3.6 mmlu pro law r25 19b a3b q4 k m
Qwen · JThomas-CoE
Params19.4B
Context256K
Q4_K_M13.2 GB
ReasoningTool use
GE
coe gemma4 business mmlu pro 14b a4b q4
Gemma · JThomas-CoE
Params14.4B
Context256K
Q4_K_M10.4 GB
GGUF
QW
coe qwen3.5 physics 18b a3b
Qwen · JThomas-CoE
Params19.8B
Context256K
Q4_K_M13.4 GB
ReasoningTool use
GE
coe gemma4 python hc 14b a4b q8 0
Gemma · JThomas-CoE
Params14.4B
Context256K
Smallest15.9 GB
Coding
GE
coe gemma4 law mmlu pro 14b a4b q4
Gemma · JThomas-CoE
Params14.4B
Context256K
Q4_K_M10.4 GB
GGUF
GE
coe gemma4 engineering mmlu pro 14b a4b q4
Gemma · JThomas-CoE
Params14.4B
Context256K
Q4_K_M10.4 GB
GGUF
GE
coe gemma4 web hc 14b a4b q4 k m
Gemma · JThomas-CoE
Params14.4B
Context256K
Q4_K_M10.4 GB
GGUF
GE
coe gemma4 economics mmlu pro 14b a4b q4
Gemma · JThomas-CoE
Params14.4B
Context256K
Q4_K_M10.4 GB
GGUF
GE
coe gemma4 cs mmlu pro 14b a4b q4
Gemma · JThomas-CoE
Params14.4B
Context256K
Q4_K_M10.4 GB
GGUF
GE
coe gemma4 engineering hc 14b a4b q4 k m
Gemma · JThomas-CoE
Params14.4B
Context256K
Q4_K_M10.4 GB
GGUF

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).

Keep browsing