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 Finetune 20251125_202658
Gemma · Mathieu-Thomas-JOSSET
Params6.87B
Context32K
Q4_K_M4.2 GB
GGUF
QW
qwen2.5 3b instruct text gguf 20260123 212150
Qwen · Mathieu-Thomas-JOSSET
Params3.09B
Context32K
Smallest3.3 GB
Tool use
MI
MISTRAL PATH Q8 0
Mistral · Mathieu-Thomas-JOSSET
Params23.6B
Context32K
Smallest25.1 GB
GGUF
QW
qwen2.5 3b instruct text gguf 20260128 112231
Qwen · Mathieu-Thomas-JOSSET
Params3.09B
Context32K
Smallest3.3 GB
Tool use
QW
qwen2.5 3b instruct text gguf 20260128 051431
Qwen · Mathieu-Thomas-JOSSET
Params3.09B
Context32K
Smallest3.3 GB
Tool use
PA
Pathfinderrr_20250501
Pathfinderrr · Mathieu-Thomas-JOSSET
Params596M
Context40K
Smallest0.6 GB
ReasoningTool use
LL
LLMIKE
Llmike · Mathieu-Thomas-JOSSET
Params3.09B
Context32K
Smallest3.3 GB
GGUF
LL
Llmiked_20260219_125611
Llmiked · Mathieu-Thomas-JOSSET
Params3.21B
Context128K
Smallest3.4 GB
GGUF
MI
MISTRAL PATH Q4 K M
Mistral · Mathieu-Thomas-JOSSET
Params23.6B
Context32K
Q4_K_M14.3 GB
GGUF
QW
PT QWEN3 4B_20260224_122932
Qwen · Mathieu-Thomas-JOSSET
Params8.19B
Context32K
Smallest8.7 GB
GGUF
QW
qwen2.5 3b instruct text gguf 20260128 054309
Qwen · Mathieu-Thomas-JOSSET
Params3.09B
Context32K
Smallest3.3 GB
Tool use
QW
qwen2.5 3b instruct text gguf 20260128 213048
Qwen · Mathieu-Thomas-JOSSET
Params3.09B
Context32K
Smallest3.3 GB
Tool use
QW
qwen2.5 3b instruct text gguf 20260128 043924
Qwen · Mathieu-Thomas-JOSSET
Params3.09B
Context32K
Smallest3.3 GB
Tool use
QW
qwen2.5 3b instruct text gguf 20260128 033527
Qwen · Mathieu-Thomas-JOSSET
Params3.09B
Context32K
Smallest3.3 GB
Tool use
QW
qwen2.5 3b instruct text gguf 20260128 043017
Qwen · Mathieu-Thomas-JOSSET
Params3.09B
Context32K
Smallest3.3 GB
Tool use

Keep browsing