GGUF models: gemma license

5164 GGUF models listed under the gemma license on Hugging Face. Always read the license text before commercial use. Sizes run from 3M to 177B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
GE
Gemma 4 26B A4B It
Gemma · DuoNeural
Params25.2B
Context256K
Smallest13.3 GB
ReasoningTool use
GE
Gemma 3 27b It Abliterated
Gemma · NovNovikov
Params27B
Context128K
Q4_K_M16.5 GB
Vision
GE
Gemma 3 12b It
Gemma · tatsuyaaaaaaa
Params11.8B
Context128K
Q4_K_M7.3 GB
GGUF
GE
The Omega Directive G 12B v1.0
Gemma · fl-15
Params11.8B
Context128K
Q4_K_M7.3 GB
GGUF
GE
Gemma 3 27b It
Gemma · AmpereComputing
Params27B
Context128K
Smallest27.7 GB
Vision
GE
gemma 3n E2B gguf q4 k m
Gemma · keisuke-miyako
Params4.46B
Context32K
Q4_K_M2.8 GB
GGUF
GE
Gemma3 Malignant.Schism 1B
Gemma · mradermacher
Params1B
Context32K
Q4_K_M0.8 GB
GGUF
GE
gemma 4 12B it Claude 4.6 4.8 Opus
Gemma · maxkru92
Params11.9B
Context128K
Q4_K_M7.4 GB
ReasoningTool use
GE
gemma 7b openhermes v0.80
Gemma · tensorblock
Params8.54B
Context8K
Smallest3.5 GB
Tool use
GE
pigeon gemma 4 dictation
Gemma · BadXStudio
Params4.65B
Context128K
Q4_K_M3.4 GB
Reasoning
GE
Gemma 2 Baku Finetune
Gemma · mradermacher
Params2.61B
Context125K
Q4_K_M1.7 GB
GGUF
GE
MT Gen4 gemma 2 9B
Gemma · mradermacher
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
GE
bggpt 4b hostile heretic
Gemma · l-lyubenov
Params3.88B
Context128K
Q4_K_M2.5 GB
GGUF
GE
gemma 3 4b it eme
Gemma · Argwn335
Params3.88B
Context128K
Q4_K_M2.5 GB
GGUF
GE
GemCod Zircon 270M XM
Gemcod · mradermacher
Params268M
Context32K
Q4_K_M0.3 GB
Coding
GE
Gemma 2 2b It
Gemma · 1bit-MONSTER
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
GE
gemma 4 19b e4b it REAP heretic APEX mini
Gemma · Benjamin-Wegener
Params18.4B
Context256K
Smallest11.7 GB
CodingReasoningTool use
GE
gemma 2 2b fa v2
Gemma · mradermacher
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
GE
gemma 3 1B reasoning en ft v1
Gemma · CALISTA-INDUSTRY
Params1B
Context32K
Smallest2.0 GB
ReasoningVision
GE
gemma 4 E2B finetune
Gemma · helenk
Params4.63B
Context128K
Q4_K_M3.4 GB
Reasoning
GE
Gemma 7b Aps It
Gemma · lmstudio-community
Params8.54B
Context8K
Q4_K_M5.3 GB
GGUF
GE
Gemma 2 2b It
Gemma · bullerwins
Params2.61B
Context8K
Smallest2.2 GB
GGUF
DA
datagemma rag 27b it
Datagemma · tensorblock
Params27.2B
Context8K
Smallest10.4 GB
GGUF
GE
gemma 3 1b pt qat q4 0
Gemma · google
Params1B
Context32K
Smallest1.0 GB
GGUF
FU
prevon pulse mk5
Functiongemma · PrevonFounder
Params268M
Context32K
Smallest0.3 GB
Tool use
YA
YanoljaNEXT Rosetta 12B 2510
Yanoljanext · mradermacher
Params12.8B
Context128K
Q4_K_M7.9 GB
GGUF
TE
Tema_Q X Thinking
Tema · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
ReasoningTool use
GE
Cognitivecomputations.Dolphin 2.9.4 Gemma2 2b
Gemma · DevQuasar-5
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
GE
gemma2 it 2b jpn Q4 K M chunked
Gemma · BoscoTheDog
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
GE
nirajandhakal/gemma-2b-base
Gemma · featherless-ai-quants
Params2.51B
Context8K
Q4_K_M1.6 GB
GGUF

Keep browsing