Gemma
by Google · Model · Language & code models
mixed
Solid small open model for documents and images, but not the leader
Big update fixes 11 issues: tool calling, chat formatting, thinking retention, vision, speed; same model names and weights
AccessOpen weightsNeeds~6.7 GBDownloadabout 6.7 GB
Why we say so
Arena places Gemma 4 third among open weights on documents (1434) and vision (1279), behind Kimi K2.6, MiniMax M3 Flash and GLM-5.3. Liquid AI claims its own LFM 2.5 beats Gemma 4, but that is a maker's claim. MIT authors noted Gemma lacked the looping problem their editing fixed in other models, and no hands-on reviews are on record.
Ranks #3 for documents (open weights) · #3 for image understanding (open weights)
Evidence
- Nov 9#3 on Arena document among open weights (1434)
- Nov 9#3 on Arena vision among open weights (1279)
- Nov 8Weight-space editing by Astra could not improve Gemma, which lacked the repetitive-loop problem
- Oct 11Gemma 4 used as an agent that plans hypotheses, writes pipelines and runs analysis in the Botanic 1 system
- Sep 13#3 on Arena document among open weights (1425)
Show all 11
- Sep 3Gemma 4 31B on Cerebras praised for instant answers and intent understanding in agentic apps, via Kagi
- Aug 25Commenter asks whether Gemma 4 E4B would be more practical than 3B-active Qwen MoE on a Pi
- Aug 18Gemma 4 serves as the text encoder for LTX 2.5
- Jul 184-bit QAT 12B GGUF from Unsloth is 6.7 GB versus about 24 GB full precision; runs on one GPU
- Jul 184-bit QAT via Hermes Agent found the planted port-draft clearance bug (+0.5 instead of -0.5) unprompted and proved the fix
- Jul 17Configurable vision token budget: choose how many tokens an image gets, from low-cost 70 up to 1120 for OCR and fine text
Cost to run
Alternatives
More Gemma
Built on Gemma