GGUF models by Mathieu-Thomas-JOSSET

75 GGUF models quantized by Mathieu-Thomas-JOSSET on Hugging Face. Sizes run from 596M to 23.6B parameters. The longest trained context is 128K tokens.

Most downloadedNewestLargestLongest contextSmallest
GE
gemma 3n text gguf3
Gemma · Mathieu-Thomas-JOSSET
Params3.88B
Context128K
Smallest4.1 GB
Vision
PH
joke finetome model gguf phi4 20260111 025151
Phi · Mathieu-Thomas-JOSSET
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
PH
joke finetome model gguf phi4 20260111 113458
Phi · Mathieu-Thomas-JOSSET
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
PH
joke finetome model gguf phi4 20260111 081117
Phi · Mathieu-Thomas-JOSSET
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
PH
joke finetome model gguf phi4 20260109 070918
Phi · Mathieu-Thomas-JOSSET
Params14.7B
Context16K
Q4_K_M8.9 GB
GGUF
PH
joke finetome model gguf phi4 20260108 044416
Phi · Mathieu-Thomas-JOSSET
Params14.7B
Context16K
Q4_K_M8.9 GB
GGUF
LL
joke finetome model gguf phi4 20260112 114159
Llama · Mathieu-Thomas-JOSSET
Params8.03B
Context128K
Smallest8.5 GB
Tool use
PH
joke finetome model gguf phi4 20260109 044903
Phi · Mathieu-Thomas-JOSSET
Params14.7B
Context16K
Q4_K_M8.9 GB
GGUF
PH
joke finetome model gguf phi4 20260110 090947
Phi · Mathieu-Thomas-JOSSET
Params14.7B
Context16K
Q4_K_M8.9 GB
GGUF
PH
joke finetome model gguf phi4 20260111 061344
Phi · Mathieu-Thomas-JOSSET
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
GE
Gemma 3n E4B Joke
Gemma · Mathieu-Thomas-JOSSET
Params6.87B
Context32K
Smallest7.4 GB
GGUF
PH
joke finetome model gguf phi4 20260110 114052
Phi · Mathieu-Thomas-JOSSET
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
GE
Gemma 3n E4B Joke55
Gemma · Mathieu-Thomas-JOSSET
Params6.87B
Context32K
Q4_K_M4.2 GB
GGUF
PH
joke finetome model gguf phi4 20260107 044440
Phi · Mathieu-Thomas-JOSSET
Params14.7B
Context16K
Q4_K_M8.9 GB
GGUF
GE
gemma 3n text
Gemma · Mathieu-Thomas-JOSSET
Params6.87B
Context32K
Smallest7.4 GB
Vision
GE
Gemma 3n E4B Joke4
Gemma · Mathieu-Thomas-JOSSET
Params6.87B
Context32K
Smallest7.4 GB
GGUF
LL
joke finetome model gguf phi4 20260110 043838
Llama · Mathieu-Thomas-JOSSET
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
PH
joke finetome model gguf phi4 20260107 235201
Phi · Mathieu-Thomas-JOSSET
Params14.7B
Context16K
Q4_K_M8.9 GB
GGUF
QW
qwen2.5 3b instruct text gguf 20260122 023745
Qwen · Mathieu-Thomas-JOSSET
Params3.09B
Context32K
Smallest3.3 GB
Tool use
QW
qwen2.5 3b instruct text gguf 20260121 031247
Qwen · Mathieu-Thomas-JOSSET
Params3.09B
Context32K
Smallest3.3 GB
Tool use
PH
joke finetome model gguf phi4 20260106 235111
Phi · Mathieu-Thomas-JOSSET
Params14.7B
Context16K
Q4_K_M8.9 GB
GGUF
QW
qwen2.5 1.5b instruct text gguf 20260123 012034
Qwen · Mathieu-Thomas-JOSSET
Params1.54B
Context32K
Smallest1.6 GB
Tool use
PH
joke finetome model gguf phi4 20260112 081758
Phi · Mathieu-Thomas-JOSSET
Params14.7B
Context16K
Smallest15.6 GB
GGUF
PH
joke finetome model gguf phi4 20260106 093459
Phi · Mathieu-Thomas-JOSSET
Params14.7B
Context16K
Q4_K_M8.9 GB
GGUF
QW
qwen2.5 3b instruct text gguf 20260121 144614
Qwen · Mathieu-Thomas-JOSSET
Params3.09B
Context32K
Smallest3.3 GB
Tool use
QW
qwen2.5 3b instruct text gguf 20260122 010546
Qwen · Mathieu-Thomas-JOSSET
Params3.09B
Context32K
Smallest3.3 GB
Tool use
PH
joke finetome model gguf phi4 20260106 065852
Phi · Mathieu-Thomas-JOSSET
Params14.7B
Context16K
Q4_K_M8.9 GB
GGUF
PH
phi4 grpo gguf q8
Phi · Mathieu-Thomas-JOSSET
Params14.7B
Context16K
Smallest15.6 GB
GGUF
LL
llmike_BEST_20260220_202004
Llmike · Mathieu-Thomas-JOSSET
Params3.21B
Context128K
Smallest3.4 GB
GGUF
PH
joke finetome model gguf phi4 20260106 111207
Phi · Mathieu-Thomas-JOSSET
Params14.7B
Context16K
Q4_K_M8.9 GB
GGUF

About Mathieu-Thomas-JOSSET on Hugging Face

Mathieu-Thomas-JOSSET has published 75 GGUF models that ggufmodels.com tracks, across families such as Phi, Qwen and Gemma. The most downloaded are gemma 3n text gguf3, joke finetome model gguf phi4 20260111 025151 and joke finetome model gguf phi4 20260111 113458.

The quants Mathieu-Thomas-JOSSET publishes most often are Q8_0 (38), Q4_K_M (37) and BF16 (6). Their Q4_K_M files range from 0.8 to 14.3 GB. Parameter counts run from 596M to 23.6B, and the longest trained context window is 128K tokens.

Frequently asked questions

What GGUF models has Mathieu-Thomas-JOSSET published?

75 models are listed here, mainly from the Phi, Qwen and Gemma families. The most downloaded is gemma 3n text gguf3.

Which quants does Mathieu-Thomas-JOSSET publish?

The most common are Q8_0 (38 models), Q4_K_M (37 models) and BF16 (6 models).

Keep browsing