GGUF models by cPilotGod

66 GGUF models quantized by cPilotGod on Hugging Face. Sizes run from 268M to 1570B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
BG
baai bge reranker v2 m3 m3
BGE · cPilotGod
Params568M
Context8K
Q4_K_M0.4 GB
Embedding
BG
baai bge m3 568m
BGE · cPilotGod
Params567M
Context8K
Q4_K_M0.4 GB
Embedding
MI
mistral codestral 22b
Mistral · cPilotGod
Params22.2B
Context32K
Q4_K_M13.3 GB
Coding
MI
mistral devstral 2 24b
Mistral · cPilotGod
Params23.6B
Context384K
Q4_K_M14.3 GB
CodingTool use
MI
mistral devstral 23 6b
Mistral · cPilotGod
Params23.6B
Context128K
Q4_K_M14.3 GB
CodingTool use
DE
deepseek deepseek r1 distill 7b
DeepSeek · cPilotGod
Params7.62B
Context128K
Q4_K_M4.7 GB
ReasoningTool use
BA
baidu ernie 4 5 21b
Baidu · cPilotGod
Params21.8B
Context128K
Q4_K_M13.3 GB
GGUF
LF
LFM2 24B A2B
Lfm · cPilotGod
Params23.8B
Context125K
Q4_K_M14.4 GB
Tool use
GE
google gemma 3 27b
Gemma · cPilotGod
Params27B
Context128K
Q4_K_M16.5 GB
GGUF
DE
deepseek deepseek r1 distill 8b
DeepSeek · cPilotGod
Params8.03B
Context128K
Q4_K_M4.9 GB
ReasoningTool use
MI
mistral devstral 2 123b
Mistral · cPilotGod
Params125B
Context256K
Q4_K_M74.9 GB
CodingTool use
DE
deepseek deepseek v4 1 6t pro
DeepSeek · cPilotGod
Params1570B
Context1024K
Q4_K_M954.6 GB
ReasoningTool use
DE
deepseek deepseek r1 distill 70b
DeepSeek · cPilotGod
Params70.6B
Context128K
Q4_K_M42.5 GB
ReasoningTool use
MI
mistral magistral 24b
Mistral · cPilotGod
Params23.6B
Context40K
Q4_K_M14.3 GB
Reasoning
MI
mistral ai nvidia mistral nemo 12b
Mistral · cPilotGod
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
PH
microsoft phi 4 reasoning 14 7b
Phi · cPilotGod
Params14.7B
Context32K
Q4_K_M9.1 GB
Reasoning
GE
google gemma 4 7 9b
Gemma · cPilotGod
Params7.52B
Context128K
Q4_K_M5.0 GB
ReasoningTool use
PH
microsoft phi 4 14b
Phi · cPilotGod
Params14.7B
Context16K
Q4_K_M8.9 GB
GGUF
MI
mistral devstral 24b
Mistral · cPilotGod
Params23.6B
Context384K
Q4_K_M14.3 GB
CodingTool use
DE
deepseek deepseek r1 distill 32b
DeepSeek · cPilotGod
Params32.8B
Context128K
Q4_K_M19.9 GB
ReasoningTool use
DE
deepseek deepseek r1 distill 14b
DeepSeek · cPilotGod
Params14.8B
Context128K
Q4_K_M9.0 GB
ReasoningTool use
BY
bytedance seed oss 36b
Bytedance · cPilotGod
Params36.2B
Context512K
Q4_K_M21.8 GB
ReasoningTool use
NE
Nvidia-Nemotron-3-Super-120B-A12B
Nemotron · cPilotGod
Params121B
Context1024K
Q4_K_M82.5 GB
ReasoningTool use
GE
google gemma 3 270m
Gemma · cPilotGod
Params268M
Context32K
Q4_K_M0.3 GB
GGUF
PH
microsoft phi 4 3b
Phi · cPilotGod
Params3.84B
Context128K
Q4_K_M2.5 GB
Tool use
GE
google gemma 3 12b
Gemma · cPilotGod
Params11.8B
Context128K
Q4_K_M7.3 GB
GGUF
QW
qwen36 35b a3b dflash draft
Qwen · cPilotGod
Params474M
Context256K
Q4_K_M0.3 GB
ReasoningTool use
GP
Gpt-Oss-Safeguard-20B
gpt-oss · cPilotGod
Params20.9B
Context128K
Q4_K_M11.6 GB
Tool use
LL
meta llama 3 3 70b
Llama · cPilotGod
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
OL
allenai olmocr 2 7b
OLMo · cPilotGod
Params7.62B
Context125K
Q4_K_M4.7 GB
GGUF

About cPilotGod on Hugging Face

cPilotGod has published 66 GGUF models that ggufmodels.com tracks, across families such as Mistral, Gemma and Qwen. The most downloaded are baai bge reranker v2 m3 m3, baai bge m3 568m and mistral codestral 22b.

The quants cPilotGod publishes most often are Q4_K_M (63), Q8_0 (59), Q6_K (56) and Q5_K_M (56). Their Q4_K_M files range from 0.3 to 954.6 GB. Parameter counts run from 268M to 1570B, and the longest trained context window is 1024K tokens.

Frequently asked questions

What GGUF models has cPilotGod published?

66 models are listed here, mainly from the Mistral, Gemma and Qwen families. The most downloaded is baai bge reranker v2 m3 m3.

Which quants does cPilotGod publish?

The most common are Q4_K_M (63 models), Q8_0 (59 models), Q6_K (56 models) and Q5_K_M (56 models).

Keep browsing