Resources

Discord server

pinned

❤️ 5

#10 opened 18 days ago by

HauhauCS

LMStudio 0.4.12 Failed to load multimodel.

#22 opened about 21 hours ago by

MinagiCN

What happened to the Gemma 4-26b and 31b launch?

#21 opened 4 days ago by

rikafurute

Model quality is good

#20 opened 7 days ago by

SDDian

Android Application default model

#19 opened 7 days ago by

jegly

No reasoning?

#18 opened 8 days ago by

James2874

Q8_K_P can't be downloaded with ollama

#17 opened 9 days ago by

tqdeas28

Update?

#16 opened 12 days ago by

popeyed

IQ4_XS vs. Q5_K_P

#15 opened 13 days ago by

Data-vanOrtus

Not able to load the model in Ollama

➕👍 5

#14 opened 13 days ago by

gulaz

Full Weights

👍 1

#12 opened 17 days ago by

iSkye

Did the mmproj file also need uncensoring or is it used as is?

#11 opened 17 days ago by

popeyed

🚀 Starting Agent Loop Tool Efficiency Test

🔥 2

#9 opened 18 days ago by

bukit

Gemma license?

👍 1

#7 opened 19 days ago by

Perpetuity7

Issue not found in original model: model stops after thinking

#6 opened 19 days ago by

IgnisIncendio

latency is too long in llama.cpp

#5 opened 19 days ago by

AMator

Q4_0 Quant?

#4 opened 19 days ago by

elpirater312

Any ETA on the bigger (31B, 26B) Gemma 4 models?

👍 2

#3 opened 20 days ago by

roe2

Unable to load the model in LM Studio

#2 opened 20 days ago by

euzen

Unclipped ggufs

#1 opened 20 days ago by

RyanoSaurus-Wrex