GGUF models by C10X

51 GGUF models quantized by C10X on Hugging Face. Sizes run from 9M to 30.5B parameters. The longest trained context is 256K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen2.5 1.5B Claude GGUF
Qwen · C10X
Params1.54B
Context32K
Smallest1.6 GB
Tool use
GE
Gemma 3 finetuneSSD
Gemma · C10X
Params1.78B
Context24K
Smallest1.9 GB
Tool use
DE
DeepSeek R1 Distill Llama 8B
DeepSeek · C10X
Params8.03B
Context128K
Q4_K_M4.9 GB
ReasoningTool use
NA
Nanbeige4 3B Thinking 2511 Claude 4.5 Opus High Reasoning Distill Heretic
Nanbeige · C10X
Params3.93B
Context64K
Smallest4.2 GB
Reasoning
NA
Nanbeige4 3B Thinking 2511 Claude 4.5 Opus High Reasoning Distill
Nanbeige · C10X
Params3.93B
Context64K
Smallest4.2 GB
ReasoningTool use
NA
Nanbeige4 3B Thinking 2511 Claude 4.5 Opus High Reasoning Distill V2 Heretic
Nanbeige · C10X
Params3.93B
Context64K
Smallest4.2 GB
Reasoning
CL
Claude3.5 4B Instruct
Claude · C10X
Params4.02B
Context256K
Smallest4.3 GB
GGUF
QW
qwq Q8 0
Qwen · C10X
Params494M
Context32K
Smallest0.5 GB
ReasoningTool use
QW
Qwen3 4B Thinking 2507 Claude 4.5 Opus High Reasoning V2
Qwen · C10X
Params4.02B
Context256K
Smallest4.3 GB
ReasoningTool use
FA
Falcon H1 0.5B Instruct
Falcon · C10X
Params521M
Context16K
Q4_K_M0.3 GB
GGUF
TO
Tongyi DeepResearch 30B A3B
Tongyi · C10X
Params30.5B
Context128K
Q4_K_M18.6 GB
GGUF
UI
UIGEN T3 4B Preview MAX
Uigen · C10X
Params4.02B
Context40K
Q4_K_M2.5 GB
ReasoningTool use
QW
Qwen2.5 1.5B Claude
Qwen · C10X
Params1.54B
Context32K
Smallest1.6 GB
Tool use
QW
Qwen3 8B Code Interpreter
Qwen · C10X
Params8.19B
Context40K
Q4_K_M5.0 GB
CodingReasoningTool use
WH
whisper tiny tr
Whisper · C10X
Params—
Context—
Smallest0.2 GB
GGUF
QR
QR1.52
C10X
Params1.54B
Context32K
Q4_K_M1.0 GB
Tool use
GE
Gemma 3 4b It Qat Q4_0 Unquantized
Gemma · C10X
Params3.88B
Context128K
Smallest1.7 GB
Vision
QR
QR
C10X
Params1.54B
Context32K
Q4_K_M1.0 GB
Tool use
QW
Qwen3 80m Tinystories
Qwen · C10X
Params83M
Context512
Smallest0.1 GB
ReasoningTool use
QW
qwenr11
Qwen · C10X
Params1.54B
Context32K
Q4_K_M1.0 GB
Tool use
GE
Gemma 3 Sft
Gemma · C10X
Params1B
Context32K
Smallest1.1 GB
GGUF
QW
Qwen2.5 1.5B Claude Dpo
Qwen · C10X
Params1.54B
Context32K
Smallest1.6 GB
Tool use
QW
Qwq 0.5b
Qwen · C10X
Params494M
Context32K
Smallest0.5 GB
ReasoningTool use
QW
Qwen2.5 1.5B Instruct
Qwen · C10X
Params1.54B
Context32K
Smallest1.6 GB
Tool use
MI
r1 mini
Mini · C10X
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
QW
Qwen3 4B KernalWriter V0.1
Qwen · C10X
Params4.02B
Context256K
Smallest4.3 GB
GGUF
QW
Qwen3 4B Thinking 2507 Opus
Qwen · C10X
Params4.02B
Context256K
Smallest4.3 GB
ReasoningTool use
GP
Gpt2 7000
Gpt · C10X
Params124M
Context1K
Smallest0.1 GB
GGUF
QW
QwenCOT 1512 Q4 K M
Qwen · C10X
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
QW
Qwen3 4B Thinking 2507 DFT
Qwen · C10X
Params4.02B
Context256K
Smallest4.3 GB
ReasoningTool use

About C10X on Hugging Face

C10X has published 51 GGUF models that ggufmodels.com tracks, across families such as Qwen, Gemma and Nanbeige. The most downloaded are Qwen2.5 1.5B Claude GGUF, Gemma 3 finetuneSSD and DeepSeek R1 Distill Llama 8B.

The quants C10X publishes most often are Q8_0 (32), Q4_K_M (18), F16 (4) and Q4_0 (1). Their Q4_K_M files range from 0.3 to 18.6 GB. Parameter counts run from 9M to 30.5B, and the longest trained context window is 256K tokens.

Frequently asked questions

What GGUF models has C10X published?

51 models are listed here, mainly from the Qwen, Gemma and Nanbeige families. The most downloaded is Qwen2.5 1.5B Claude GGUF.

Which quants does C10X publish?

The most common are Q8_0 (32 models), Q4_K_M (18 models), F16 (4 models) and Q4_0 (1 models).

Keep browsing