GGUF models by ijohn07

106 GGUF models quantized by ijohn07 on Hugging Face. Sizes run from 773M to 34.7B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen3 14B Uncensored
Qwen · ijohn07
Params14.8B
Context40K
Q4_K_M9.0 GB
GGUF
HA
Harness 1
Harness · ijohn07
Params20.9B
Context128K
Q4_K_M15.8 GB
GGUF
QW
Qwen3 Coder 30B A3B Instruct FP8
Qwen · ijohn07
Params30.5B
Context256K
Q4_K_M18.6 GB
CodingTool use
DE
DeepSeek R1 Distill Qwen 1.5B Fully Uncensored
DeepSeek · ijohn07
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
HU
Huihui NeoHorse 1 4B Abliterated
Huihui · ijohn07
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool use
ME
MedraN E4B Uncensored EP7
Medran · ijohn07
Params6.87B
Context32K
Smallest7.4 GB
ReasoningVision
ME
MedraN E4B Uncensored EP7
Medran · ijohn07
Params6.87B
Context32K
Q4_K_M4.2 GB
ReasoningVision
DE
DeepSeek Coder V2 Lite Instruct
DeepSeek · ijohn07
Params15.7B
Context160K
Smallest11.9 GB
Coding
QW
Qwen2.5 3B Instruct
Qwen · ijohn07
Params3.09B
Context32K
Smallest3.3 GB
Tool use
QW
Qwen2.5 Coder 1.5B
Qwen · ijohn07
Params1.54B
Context32K
Smallest1.6 GB
CodingTool use
NE
NVIDIA Nemotron 3.5 Lightning 30B A3B BF16
Nemotron · ijohn07
Params31.6B
Context1024K
Smallest24.5 GB
GGUF
BA
BADMISTRAL 1.5B Q8 0
Badmistral · ijohn07
Params1.55B
Context8K
Smallest1.7 GB
GGUF
OR
Ornith 1.0 9B Heretic
Ornith · ijohn07
Params8.95B
Context256K
Smallest9.5 GB
GGUF
DE
DeepSeek Coder V2 Lite Instruct
DeepSeek · ijohn07
Params15.7B
Context160K
Q4_K_M10.4 GB
Coding
NE
NVIDIA Nemotron 3.5 Lightning 30B A3B BF16
Nemotron · ijohn07
Params31.6B
Context1024K
Smallest33.5 GB
GGUF
QW
Qwen2.5 1.5B
Qwen · ijohn07
Params1.54B
Context32K
Smallest1.6 GB
Tool use
HO
Holo 3.1 4B
Holo · ijohn07
Params4.84B
Context256K
Q4_K_M3.1 GB
ReasoningTool useVision
OR
Ornith 1.0 9B Heretic
Ornith · ijohn07
Params8.95B
Context256K
Smallest6.5 GB
GGUF
HU
Huihui NeoHorse 1 4B Abliterated
Huihui · ijohn07
Params4.21B
Context256K
Smallest4.5 GB
ReasoningTool use
NE
NVIDIA Nemotron 3.5 Lightning 30B A3B BF16
Nemotron · ijohn07
Params31.6B
Context1024K
Smallest33.6 GB
GGUF
NE
NVIDIA Nemotron 3.5 Lightning 30B A3B BF16
Nemotron · ijohn07
Params31.6B
Context1024K
Smallest17.9 GB
GGUF
OR
Ornith 1.0 9B Heretic
Ornith · ijohn07
Params8.95B
Context256K
Smallest7.4 GB
GGUF
GE
gemma-3-12b-it-codeforces-SFT
Gemma · ijohn07
Params11.8B
Context128K
Q4_K_M7.3 GB
Reasoning
DE
DeepSeek R1 Distill Qwen 1.5B Fully Uncensored
DeepSeek · ijohn07
Params1.78B
Context128K
Smallest1.9 GB
ReasoningTool use
QW
Qwen2.5 7B
Qwen · ijohn07
Params7.62B
Context128K
Q4_K_M4.7 GB
Tool use
OR
Ornith 1.0 9B Heretic
Ornith · ijohn07
Params8.95B
Context256K
Q4_K_M5.6 GB
GGUF
TM
Tmax 4b
Tmax · ijohn07
Params4.21B
Context256K
Smallest4.5 GB
ReasoningTool use
TM
Tmax 4b
Tmax · ijohn07
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool use
TM
Tmax 9b
Tmax · ijohn07
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
HO
Holo 3.1 0.8B
Holo · ijohn07
Params1.01B
Context256K
Q4_K_M0.7 GB
ReasoningTool useVision

About ijohn07 on Hugging Face

ijohn07 has published 106 GGUF models that ggufmodels.com tracks, across families such as DeepSeek, Mistral and Qwen. The most downloaded are Qwen3 14B Uncensored, Harness 1 and Qwen3 Coder 30B A3B Instruct FP8.

The quants ijohn07 publishes most often are Q8_0 (50), Q4_K_M (25), Q6_K (16) and Q2_K (6). Their Q4_K_M files range from 0.7 to 21.2 GB. Parameter counts run from 773M to 34.7B, and the longest trained context window is 1024K tokens.

Frequently asked questions

What GGUF models has ijohn07 published?

106 models are listed here, mainly from the DeepSeek, Mistral and Qwen families. The most downloaded is Qwen3 14B Uncensored.

Which quants does ijohn07 publish?

The most common are Q8_0 (50 models), Q4_K_M (25 models), Q6_K (16 models) and Q2_K (6 models).

Keep browsing