GGUF models by Disya

62 GGUF models quantized by Disya on Hugging Face. Sizes run from 423M to 34.7B parameters. The longest trained context is 1000K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Josiefied Qwen3 30B A3B Abliterated v1
Qwen · Disya
Params30.5B
Context40K
Q4_K_M18.6 GB
GGUF
QW
The Omega Directive Qwen3 14B v1.1
Qwen · Disya
Params14.8B
Context40K
Q4_K_M9.0 GB
ReasoningRoleplayTool use
GE
Gemma 4 12B It Qat Q4_0 Unquantized Heretic
Gemma · Disya
Params11.9B
Context256K
Smallest6.7 GB
CodingReasoningTool use
OV
OvisOCR2
Ovisocr · Disya
Params752M
Context256K
Smallest0.8 GB
ReasoningTool useVision
QW
Mistral qwq 12b merge
Qwen · Disya
Params12.2B
Context128K
Q4_K_M7.5 GB
Reasoning
GE
Gemma 4 E4B It Qat Q4_0 Unquantized Heretic
Gemma · Disya
Params7.46B
Context128K
Smallest4.3 GB
CodingReasoningTool use
QW
Huihui Qwen3 4B Thinking 2507 Abliterated
Qwen · Disya
Params4.02B
Context256K
Smallest4.3 GB
Reasoning
HU
Hunyuan 0.5B Instruct
Hunyuan · Disya
Params539M
Context256K
Smallest0.6 GB
ReasoningTool use
QW
Qwen3 14B Abliterated
Qwen · Disya
Params14.8B
Context40K
Q4_K_M9.0 GB
GGUF
GE
Gemma 4 12B It Qat Q4_0 Unquantized Assistant
Gemma · Disya
Params423M
Context256K
Smallest0.3 GB
ReasoningTool use
FR
Frankenqwen3 8B 235B Dense Conversion Interleaved Untuned
Frankenqwen · Disya
Params13.6B
Context40K
Q4_K_M8.3 GB
ReasoningTool use
UI
UIGEN T3 14B Preview
Uigen · Disya
Params14.8B
Context40K
Q4_K_M9.0 GB
ReasoningTool use
AP
Apriel 1.5 15b Thinker
Apriel · Disya
Params14.4B
Context256K
Q4_K_M8.8 GB
ReasoningTool useVision
WO
WorldSim Opus 3.6 35B A3B
Worldsim · Disya
Params34.7B
Context256K
Smallest19.7 GB
ReasoningRoleplay
QW
Qwen3 30B A1.5B High Speed
Qwen · Disya
Params30.5B
Context40K
Q4_K_M18.6 GB
ReasoningTool use
QW
Qwen3 30B A3B Instruct 2507_Pruned_REAP 15B A3B SafeTensors
Qwen · Disya
Params16B
Context256K
Smallest9.1 GB
GGUF
QW
Josiefied Qwen3 14B Abliterated v1
Qwen · Disya
Params14.8B
Context40K
Q4_K_M9.0 GB
ReasoningTool use
GL
Remnant Glm4 32b
GLM · Disya
Params32.6B
Context32K
Smallest18.7 GB
RoleplayTool use
QW
Qwen3.5 9B RpRMax v1
Qwen · Disya
Params8.95B
Context256K
Smallest7.4 GB
ReasoningTool useVision
QW
Qwen3.5 4B RpRMax v1
Qwen · Disya
Params4.21B
Context256K
Smallest4.5 GB
ReasoningTool useVision
DA
12b mn dans reasoning test 5 Q4 K M
Dans · Disya
Params12.2B
Context1000K
Q4_K_M7.5 GB
Reasoning
HU
Hunyuan 1.8B Instruct
Hunyuan · Disya
Params1.79B
Context256K
Smallest1.9 GB
ReasoningTool use
QW
Magnum Qwen3 4b
Qwen · Disya
Params4.02B
Context32K
Smallest4.3 GB
GGUF
IM
Impish_Longtail_12B
Impish · Disya
Params12.2B
Context1000K
Smallest8.7 GB
GGUF
MA
Marco Nano Instruct
Marco · Disya
Params8B
Context32K
Smallest7.2 GB
ReasoningTool use
SH
shuttle 2.5 mini Q4 K M
Shuttle · Disya
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
QW
Qwen3 14B CreativeWrite Merge
Qwen · Disya
Params14.8B
Context40K
Q4_K_M9.0 GB
GGUF
PA
PaCoRe 8B
Pacore · Disya
Params8.19B
Context320K
Q4_K_M5.0 GB
GGUF
QW
Qwen2.5 1M RP Context Merge
Qwen · Disya
Params14.8B
Context986K
Q4_K_M9.0 GB
RoleplayTool use
HU
Hunyuan 4B Instruct
Hunyuan · Disya
Params4.22B
Context256K
Smallest4.5 GB
ReasoningTool use

About Disya on Hugging Face

Disya has published 62 GGUF models that ggufmodels.com tracks, across families such as Qwen, Mistral and Hunyuan. The most downloaded are Josiefied Qwen3 30B A3B Abliterated v1, The Omega Directive Qwen3 14B v1.1 and Gemma 4 12B It Qat Q4_0 Unquantized Heretic.

The quants Disya publishes most often are Q4_K_M (24), Q8_0 (16), Q5_K_M (6) and Q4_0 (6). Their Q4_K_M files range from 5.0 to 18.6 GB. Parameter counts run from 423M to 34.7B, and the longest trained context window is 1000K tokens.

Frequently asked questions

What GGUF models has Disya published?

62 models are listed here, mainly from the Qwen, Mistral and Hunyuan families. The most downloaded is Josiefied Qwen3 30B A3B Abliterated v1.

Which quants does Disya publish?

The most common are Q4_K_M (24 models), Q8_0 (16 models), Q5_K_M (6 models) and Q4_0 (6 models).

Keep browsing