GGUF models by Goekdeniz-Guelmez

54 GGUF models quantized by Goekdeniz-Guelmez on Hugging Face. Sizes run from 596M to 14.8B parameters. The longest trained context is 128K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen2 1.5B Instruct
Qwen · Goekdeniz-Guelmez
Params1.78B
Context32K
Q4_K_M1.1 GB
GGUF
QW
Josiefied Qwen2.5 1.5B Instruct abliterated v3
Qwen · Goekdeniz-Guelmez
Params1.54B
Context32K
Q4_K_M1.0 GB
GGUF
QW
Josiefied Qwen2.5 14B Instruct Abliterated v4
Qwen · Goekdeniz-Guelmez
Params14.8B
Context32K
Q4_K_M9.0 GB
GGUF
QW
Josiefied Qwen2.5 1.5B Instruct Abliterated v1
Qwen · Goekdeniz-Guelmez
Params1.5B
Context32K
Q4_K_M1.1 GB
GGUF
QW
Josiefied Qwen2.5 7B Instruct Abliterated v2
Qwen · Goekdeniz-Guelmez
Params7B
Context32K
Q4_K_M4.7 GB
GGUF
MI
J.O.S.I.E.3 Beta5 slerp
Mistral · Goekdeniz-Guelmez
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
GE
dolphin 2.8 gemma 2b
Gemma · Goekdeniz-Guelmez
Params3.03B
Context8K
Q4_K_M1.9 GB
GGUF
EI
J.O.S.I.E.3 Beta4 slerp
Einstein · Goekdeniz-Guelmez
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
QW
Josiefied Qwen2.5 Coder 7B Instruct Abliterated v1
Qwen · Goekdeniz-Guelmez
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingTool use
DP
J.O.S.I.E.V4O 1.5b Dpo Stage1 v1
Dpo · Goekdeniz-Guelmez
Params1.5B
Context32K
Q4_K_M1.0 GB
GGUF
QW
Josiefied Qwen2.5 1.5B Instruct abliterated v2
Qwen · Goekdeniz-Guelmez
Params1.54B
Context32K
Q4_K_M1.0 GB
Tool use
QW
Qwen2 0.5B Instruct
Qwen · Goekdeniz-Guelmez
Params630M
Context32K
Q4_K_M0.5 GB
GGUF
QW
Josiefied Qwen3 4B Abliterated v1
Qwen · Goekdeniz-Guelmez
Params4.02B
Context40K
Q4_K_M2.5 GB
ReasoningTool use
MI
Hyperion 2.1 Mistral 7B
Mistral · Goekdeniz-Guelmez
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
TH
ThoughtStream 4B v0.2
Thoughtstream · Goekdeniz-Guelmez
Params4B
Context8K
Q4_K_M2.4 GB
GGUF
QW
Josiefied Qwen2.5 0.5B Instruct Abliterated v1
Qwen · Goekdeniz-Guelmez
Params630M
Context32K
Q4_K_M0.5 GB
Tool use
QW
Josiefied Qwen3 1.7B Abliterated v1
Qwen · Goekdeniz-Guelmez
Params1.72B
Context40K
Smallest1.1 GB
ReasoningTool use
QW
Qwen2 7B Instruct
Qwen · Goekdeniz-Guelmez
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
QW
Josiefied Qwen2.5 3B Instruct Abliterated v1
Qwen · Goekdeniz-Guelmez
Params3.4B
Context32K
Q4_K_M2.1 GB
Tool use
MI
Hyperion 2.0 Mistral 7B
Mistral · Goekdeniz-Guelmez
Params7.24B
Context32K
Q4_K_M4.4 GB
Coding
MI
NousResearch Genstruct 7B only
Mistral · Goekdeniz-Guelmez
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
QW
Josiefied Qwen3 0.6B Abliterated v1
Qwen · Goekdeniz-Guelmez
Params596M
Context40K
Smallest0.4 GB
ReasoningTool use
MI
mistral 7b grok
Mistral · Goekdeniz-Guelmez
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MI
NousResearch Genstruct 7B
Mistral · Goekdeniz-Guelmez
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MI
Hercules 2.5 Mistral 7B
Mistral · Goekdeniz-Guelmez
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
JO
josiev4o-7b-stage1-v0.1
Josiev · Goekdeniz-Guelmez
Params7.62B
Context128K
Q4_K_M4.7 GB
GGUF
MI
OpenHercules 2.5 Mistral 7B
Mistral · Goekdeniz-Guelmez
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MI
J.O.S.I.E.3 Beta3 slerp
Mistral · Goekdeniz-Guelmez
Params7.24B
Context32K
Smallest3.5 GB
GGUF
MI
ChatHercules 2.5 Mistral 7B
Mistral · Goekdeniz-Guelmez
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MI
OpenHyperion 2.5 Mistral 7B
Mistral · Goekdeniz-Guelmez
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF

About Goekdeniz-Guelmez on Hugging Face

Goekdeniz-Guelmez has published 54 GGUF models that ggufmodels.com tracks, across families such as Qwen, Mistral and Stage. The most downloaded are Qwen2 1.5B Instruct, Josiefied Qwen2.5 1.5B Instruct abliterated v3 and Josiefied Qwen2.5 14B Instruct Abliterated v4.

The quants Goekdeniz-Guelmez publishes most often are Q4_K_M (45), Q4_K_S (41), Q6_K (40) and Q5_K_M (39). Their Q4_K_M files range from 0.5 to 9.0 GB. Parameter counts run from 596M to 14.8B, and the longest trained context window is 128K tokens.

Frequently asked questions

What GGUF models has Goekdeniz-Guelmez published?

54 models are listed here, mainly from the Qwen, Mistral and Stage families. The most downloaded is Qwen2 1.5B Instruct.

Which quants does Goekdeniz-Guelmez publish?

The most common are Q4_K_M (45 models), Q4_K_S (41 models), Q6_K (40 models) and Q5_K_M (39 models).

Keep browsing