GGUF models by kenonix

69 GGUF models quantized by kenonix on Hugging Face. Sizes run from 7M to 26.9B parameters. The longest trained context is 256K tokens.

Most downloadedNewestLargestLongest contextSmallest
PH
Phi 4 Mini Instruct
Phi · kenonix
Params3.84B
Context128K
Smallest2.8 GB
CodingTool use
LL
Llama 3.3 8B Thinking Gemini Flash 11000x 128k
Llama · kenonix
Params8.03B
Context128K
Q4_K_M4.9 GB
ReasoningRoleplay
LL
Llama 3.3 8B Thinking Gemini Flash 11000x 128k
Llama · kenonix
Params8.03B
Context128K
Smallest8.5 GB
ReasoningRoleplay
GE
Gemma 3 1b It Qat Abliterated
Gemma · kenonix
Params1B
Context32K
Q4_K_M0.8 GB
Vision
GE
gemma 3 ko 1B 1 Q8 0
Gemma · kenonix
Params1B
Context32K
Smallest1.1 GB
GGUF
GE
Gemma 3 Ko 1B Full
Gemma · kenonix
Params1B
Context32K
Smallest1.1 GB
GGUF
GE
Gemma 3 Ko 1B 2
Gemma · kenonix
Params1B
Context32K
Smallest1.1 GB
GGUF
AW
AWAXIS Think 28B
Awaxis · kenonix
Params26.9B
Context256K
Smallest28.6 GB
ReasoningTool use
GE
Gemma 3 Ko
Gemma · kenonix
Params1B
Context32K
Q4_K_M0.8 GB
GGUF
GE
Gemma 3N More Math Ko2
Gemma · kenonix
Params6.87B
Context32K
Smallest4.9 GB
GGUF
GE
Gemma 3 1b It Qat Abliterated
Gemma · kenonix
Params1B
Context32K
Smallest1.1 GB
Vision
GE
Gemma 3 Ko 4B 1
Gemma · kenonix
Params3.88B
Context128K
Q4_K_M2.5 GB
GGUF
KA
Kanana Nano 2.1b Instruct
Kanana · kenonix
Params2.09B
Context8K
Smallest1.8 GB
GGUF
NE
Next 4b
Next · kenonix
Params3.88B
Context128K
Smallest2.8 GB
CodingVision
NE
Next 4b
Next · kenonix
Params3.88B
Context128K
Smallest3.2 GB
CodingVision
DA
Darwin 9B KOREA
Darwin · kenonix
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
GE
Gemma 3 Ko 4B 1 Qat3
Gemma · kenonix
Params3.88B
Context128K
Q4_K_M2.5 GB
GGUF
KA
Kanana Nano 2.1b Instruct
Kanana · kenonix
Params2.09B
Context8K
Smallest2.2 GB
GGUF
GE
Gemma 3N More Math Ko2
Gemma · kenonix
Params6.87B
Context32K
Smallest5.7 GB
GGUF
GE
Gemma 3 Ko
Gemma · kenonix
Params1B
Context32K
Smallest1.1 GB
GGUF
KY
Kyro n1.1 3B Q4 K M
Kyro · kenonix
Params3.09B
Context32K
Q4_K_M1.9 GB
ReasoningTool use
GE
Gemma 3 Ko 4B 1
Gemma · kenonix
Params3.88B
Context128K
Smallest4.1 GB
GGUF
GE
Gemma 3N More Math Ko
Gemma · kenonix
Params6.87B
Context32K
Smallest5.7 GB
GGUF
NE
Next 4b
Next · kenonix
Params3.88B
Context128K
Smallest4.1 GB
CodingVision
GE
Gemma 3N More Math Ko2
Gemma · kenonix
Params6.87B
Context32K
Smallest4.1 GB
GGUF
LL
Linkbricks Llama3.2 Korean cpt 3b Q6 K
Llama · kenonix
Params3.61B
Context128K
Smallest3.0 GB
Tool use
DE
DeepSeek Llama3.1 Bllossom 8
DeepSeek · kenonix
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
GE
Gemma 3N More Math Ko2
Gemma · kenonix
Params6.87B
Context32K
Q4_K_M4.2 GB
GGUF
GE
Gemma 3 Ko 1B Think 1
Gemma · kenonix
Params1B
Context32K
Smallest1.1 GB
Reasoning
GE
Gemma 3 Ko Finetune3
Gemma · kenonix
Params1B
Context32K
Smallest0.8 GB
GGUF

About kenonix on Hugging Face

kenonix has published 69 GGUF models that ggufmodels.com tracks, across families such as Gemma, Llama and Next. The most downloaded are Phi 4 Mini Instruct, Llama 3.3 8B Thinking Gemini Flash 11000x 128k and Llama 3.3 8B Thinking Gemini Flash 11000x 128k.

The quants kenonix publishes most often are Q8_0 (35), Q4_K_M (18), Q6_K (6) and Q4_0 (3). Their Q4_K_M files range from 0.8 to 16.5 GB. Parameter counts run from 7M to 26.9B, and the longest trained context window is 256K tokens.

Frequently asked questions

What GGUF models has kenonix published?

69 models are listed here, mainly from the Gemma, Llama and Next families. The most downloaded is Phi 4 Mini Instruct.

Which quants does kenonix publish?

The most common are Q8_0 (35 models), Q4_K_M (18 models), Q6_K (6 models) and Q4_0 (3 models).

Keep browsing