GGUF models by gghfez

48 GGUF models quantized by gghfez on Hugging Face. Sizes run from 8M to 2048B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
GP
Gpt Oss 120b Derestricted
gpt-oss · gghfez
Params117B
Context128K
Smallest63.4 GB
GGUF
QW
Qwen3.8 27B jacobian lens
Qwen · gghfez
Params1.65B
Context—
Smallest3.3 GB
GGUF
IN
inkling jlens
Inkling · gghfez
Params2.45B
Context—
Smallest4.9 GB
GGUF
CO
c4ai command r plus jlens
Command R · gghfez
Params9.51B
Context—
Smallest19.0 GB
GGUF
GP
Gpt Oss 20b Derestricted
gpt-oss · gghfez
Params20.9B
Context128K
Q4_K_M15.8 GB
GGUF
WI
WizardLM-2-8x22B-Beige
Wizardlm · gghfez
Params141B
Context64K
Q4_K_M85.6 GB
GGUF
CO
c4ai command r v01 jacobian lens
Command R · gghfez
Params2.62B
Context—
Smallest5.2 GB
GGUF
OP
openwebui-title-generator
Openwebui · gghfez
Params268M
Context32K
Smallest0.3 GB
GGUF
MI
MiMo V2.6 Flash MOPD jacobian lens
Mimo · gghfez
Params789M
Context—
Smallest1.6 GB
GGUF
LL
MiMo V2.5 Pro
Llama · gghfez
Params1020B
Context1024K
Smallest274.1 GB
GGUF
GE
gemma 4 12B it qat jacobian lens
Gemma · gghfez
Params693M
Context—
Smallest1.4 GB
GGUF
QW
Qwen3.8 27B
Qwen · gghfez
Params27.3B
Context256K
Smallest19.5 GB
ReasoningTool useVision
GE
Gemma 3 27b It
Gemma · gghfez
Params27B
Context128K
Smallest15.6 GB
GGUF
LU
SmartMaid 123
Lumimaid · gghfez
Params123B
Context128K
Smallest45.2 GB
GGUF
CV
cvector experiments
Cvector · gghfez
Params—
Context—
Smallest0.0 GB
GGUF
WI
WizardLM 2 22b RP
Wizardlm · gghfez
Params22.2B
Context64K
Q4_K_M13.3 GB
Roleplay
LA
Laguna XS.2 jlens
Laguna · gghfez
Params164M
Context—
Smallest0.3 GB
GGUF
GE
Gemma 3 12b It
Gemma · gghfez
Params11.8B
Context128K
Smallest6.9 GB
GGUF
GL
GLM 4.7 Derestricted v3 Q3KL
GLM · gghfez
Params358B
Context198K
Smallest172.9 GB
ReasoningTool use
MI
MiMo V2.5
Mimo · gghfez
Params309B
Context1024K
Smallest113.1 GB
ReasoningTool use
DE
DeepSeek R1 0528
DeepSeek · gghfez
Params672B
Context160K
Smallest302.5 GB
ReasoningTool use
GL
GLM 4.7 Q8
GLM · gghfez
Params358B
Context198K
Smallest381.0 GB
ReasoningTool use
QW
Qwen3.6 27B
Qwen · gghfez
Params26.9B
Context256K
Smallest28.6 GB
ReasoningTool useVision
DE
DeepSeek V3.1
DeepSeek · gghfez
Params672B
Context160K
Smallest219.0 GB
ReasoningTool use
DE
DeepSeek R1 Zero
DeepSeek · gghfez
Params672B
Context160K
Smallest302.6 GB
ReasoningTool use
DE
DeepSeek R1 Zero
DeepSeek · gghfez
Params672B
Context160K
Smallest219.0 GB
ReasoningTool use
GP
Gpt Oss 20b SOMbliterated
gpt-oss · gghfez
Params20.9B
Context128K
Smallest12.1 GB
Tool use
MI
Devstral 2 123B Instruct 2512
Mistral · gghfez
Params125B
Context256K
Smallest74.9 GB
CodingTool use
KI
Kimi K2 0905 no not X but Y cv
Kimi · gghfez
Params—
Context—
Smallest0.0 GB
GGUF
DE
DeepSeek V3.1 Base IQ2 KS
DeepSeek · gghfez
Params672B
Context160K
Smallest219.0 GB
ReasoningTool use

About gghfez on Hugging Face

gghfez has published 48 GGUF models that ggufmodels.com tracks, across families such as DeepSeek, Qwen and gpt-oss. The most downloaded are Gpt Oss 120b Derestricted, Qwen3.8 27B jacobian lens and inkling jlens.

The quants gghfez publishes most often are Q4_K_M (6), Q4_K (5), BF16 (5) and Q8_0 (4). Their Q4_K_M files range from 0.0 to 85.6 GB. Parameter counts run from 8M to 2048B, and the longest trained context window is 1024K tokens.

Frequently asked questions

What GGUF models has gghfez published?

48 models are listed here, mainly from the DeepSeek, Qwen and gpt-oss families. The most downloaded is Gpt Oss 120b Derestricted.

Which quants does gghfez publish?

The most common are Q4_K_M (6 models), Q4_K (5 models), BF16 (5 models) and Q8_0 (4 models).

Keep browsing