GGUF models by noctrex

173 GGUF models quantized by noctrex on Hugging Face. Sizes run from 1M to 396B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Huihui Qwen3 VL 4B Instruct Abliterated
Qwen · noctrex
Params4B
Context256K
Q4_K_M2.5 GB
Vision
QW
Huihui Qwen3 VL 30B A3B Instruct Abliterated
Qwen · noctrex
Params30.5B
Context256K
Q4_K_M18.6 GB
Vision
QW
Huihui Qwen3 VL 8B Instruct Abliterated
Qwen · noctrex
Params8.19B
Context256K
Q4_K_M5.0 GB
Vision
GP
Huihui gpt oss 20b abliterated v2 MXFP4 MOE
gpt-oss · noctrex
Params20.9B
Context128K
Smallest12.1 GB
Tool use
GE
Gemma 4 26B A4B It Uncensored Heretic
Gemma · noctrex
Params25.2B
Context256K
Smallest15.4 GB
Vision
LI
LightOnOCR 2 1B
Lightonocr · noctrex
Params596M
Context16K
Q4_K_M0.4 GB
Vision
LI
LightOnOCR 2 1B Ocr Soup
Lightonocr · noctrex
Params596M
Context16K
Q4_K_M0.4 GB
Vision
QW
Huihui Qwen3 VL 2B Instruct Abliterated
Qwen · noctrex
Params1.72B
Context256K
Q4_K_M1.1 GB
Vision
OP
openPangu Embedded 7B V1.1
Openpangu · noctrex
Params8.03B
Context32K
Q4_K_M4.9 GB
Embedding
GE
Gemma-4-26B-A4B-It
Gemma · noctrex
Params25.2B
Context256K
Smallest15.4 GB
Vision
LF
LFM2.5 2.6B heretic uncensored
Lfm · noctrex
Params2.7B
Context125K
Q4_K_M1.7 GB
GGUF
CH
Chandra
Chandra · noctrex
Params8.19B
Context256K
Q4_K_M5.0 GB
Tool useVision
GP
Huihui gpt oss 120b abliterated MXFP4 MOE
gpt-oss · noctrex
Params117B
Context128K
Smallest63.4 GB
Tool use
MI
Huihui Mistral Small 3.2 24B Instruct 2506 Abliterated v2
Mistral · noctrex
Params23.6B
Context128K
Q4_K_M14.3 GB
Vision
QW
Qwen3.6 35B A3B Uncensored Heretic
Qwen · noctrex
Params34.7B
Context256K
Smallest20.3 GB
Vision
QW
Qwopus3.5 9B Coder MTP
Qwopus · noctrex
Params1M
Context—
Smallest0.0 GB
GGUF
MI
Mistralai Shieldstral 1.0 3B
Mistral · noctrex
Params3.43B
Context256K
Q4_K_M2.1 GB
Vision
QW
Huihui Qwen3 VL 8B Thinking Abliterated
Qwen · noctrex
Params8.19B
Context256K
Q4_K_M5.0 GB
ReasoningTool useVision
QW
Qwen3.6 35B A3B
Qwen · noctrex
Params34.7B
Context256K
Smallest20.3 GB
Vision
QW
Huihui Qwen3 VL 4B Instruct Abliterated
Qwen · noctrex
Params4B
Context256K
Q4_K_M2.5 GB
Vision
QW
Huihui Qwen3 VL 30B A3B Thinking Abliterated
Qwen · noctrex
Params30.5B
Context256K
Q4_K_M18.6 GB
ReasoningTool useVision
OP
openPangu Embedded 1B V1.1
Openpangu · noctrex
Params1.16B
Context32K
Q4_K_M0.8 GB
Embedding
QW
Huihui Qwen3 VL 8B Instruct Abliterated
Qwen · noctrex
Params8.19B
Context256K
Q4_K_M5.0 GB
Tool useVision
MI
Mistral 7B Instruct v0.3 Abliterated
Mistral · noctrex
Params7.25B
Context32K
Q4_K_M4.4 GB
Tool use
QW
Qwen3.6 35B A3B
Qwen · noctrex
Params35.5B
Context256K
Smallest21.2 GB
GGUF
QW
Huihui Qwen3.5 35B A3B Abliterated
Qwen · noctrex
Params34.7B
Context256K
Smallest22.1 GB
ReasoningTool useVision
VE
UI Venus 1.5 8B
Venus · noctrex
Params8.19B
Context256K
Q4_K_M5.0 GB
Tool useVision
VE
UI Venus 1.5 2B
Venus · noctrex
Params2.03B
Context256K
Q4_K_M1.3 GB
Tool useVision
LI
Ling 3.0 tiny MXFP4 MOE
Ling · noctrex
Params7.89B
Context128K
Smallest4.9 GB
ReasoningTool use
MI
Mistral Nemo Instruct 2407 Heretic Noslop
Mistral · noctrex
Params12.2B
Context128K
Q4_K_M7.5 GB
Tool use

About noctrex on Hugging Face

noctrex has published 173 GGUF models that ggufmodels.com tracks, across families such as Qwen, Huihui and GLM. The most downloaded are Huihui Qwen3 VL 4B Instruct Abliterated, Huihui Qwen3 VL 30B A3B Instruct Abliterated and Huihui Qwen3 VL 8B Instruct Abliterated.

The quants noctrex publishes most often are MXFP4_MOE (120), Q8_0 (47), Q6_K (47) and Q5_K_M (46). Their Q4_K_M files range from 0.4 to 19.8 GB. Parameter counts run from 1M to 396B, and the longest trained context window is 10240K tokens.

Frequently asked questions

What GGUF models has noctrex published?

173 models are listed here, mainly from the Qwen, Huihui and GLM families. The most downloaded is Huihui Qwen3 VL 4B Instruct Abliterated.

Which quants does noctrex publish?

The most common are MXFP4_MOE (120 models), Q8_0 (47 models), Q6_K (47 models) and Q5_K_M (46 models).

Keep browsing