Gemma 3 270M
Aug 2025
Gemma 3 270MCompare inon
Benchmarks of Gemma 3 270M13
BenchmarkByScoreRank
Overall1
Knowledge4
Science2
Coding1
Documents1
Legacy · saturated or no longer reported4
No benchmark matches
—per task?
self-host onlyprice
—output speed?
32Kcontext
Ranking?
Alternatives?
ModelScoreCostPer taskWhat changes
BetterGranite 4.2 3BthinkingOpen+15%—$0.006Memory (4-bit): 0.1 GB → 1.8 GBOOpenMiniCPM5 1Bnon-thinking×33.8——Memory (4-bit): 0.1 GB → 0.5 GBBetterGranite 4.2 30BthinkingOpen+19%—$0.072Memory (4-bit): 0.1 GB → 18 GBMBetterQuasar 438B+42%—$0.15
BetterMiMo v2.5 ProthinkingOpen+23%—$0.15Memory (4-bit): 0.1 GB → 614 GBModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
Granite 4.2 3BthinkingOpen+15%—$0.006Memory (4-bit): 0.1 GB → 1.8 GBGranite 4.2 30BthinkingOpen+19%—$0.072Memory (4-bit): 0.1 GB → 18 GBMQuasar 438B+42%—$0.15MiMo v2.5 ProthinkingOpen+23%—$0.15Memory (4-bit): 0.1 GB → 614 GB
Grok 4.3high+18%—$0.21ModelScoreCostPer taskWhat changes
OMiniCPM5 1Bnon-thinkingOpen×33.8——Memory (4-bit): 0.1 GB → 0.5 GBAG9v3 3BOpen×2.6——Memory (4-bit): 0.1 GB → 1.5 GBlLFM2.5 2.6BthinkingOpen+90%—$0.35 / $0.50Memory (4-bit): 0.1 GB → 1.3 GBOMiniCPM5 2BthinkingOpen+39%——Memory (4-bit): 0.1 GB → 1.3 GBGranite 4.2 3BthinkingOpen+15%—$0.006Memory (4-bit): 0.1 GB → 1.8 GBModelScoreCostPer taskWhat changes
Gemma 3n E4B Instructnon-thinkingOpen-69%——Memory (4-bit): 0.1 GB → 3.9 GBGemma 3n E2B InstructOpen-67%——Memory (4-bit): 0.1 GB → 2.7 GBGemini 2.5 Flashnon-thinking-67%—$0.30 / $2.50Gemini 3 Flash Previewnon-thinking-67%—$0.50 / $3Gemini 2.5 Flash Preview (Sep '25)non-thinking-67%——Gemini 2.5 Prothinking-67%—$0.31DiffusionGemma 26B A4BOpen-67%—$0.05 / $0.15Memory (4-bit): 0.1 GB → 15 GBGemini 2.5 Flash Litenon-thinking-65%—$0.10 / $0.40All Google models →Run it yourself
estimateFits on✓ 8 GB (phone, laptop) · full quality✓ 16 GB · full quality✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
LicenceGemma termscommercial use with conditions
Benchmarks
all categoriesChat & Knowledge
Humanity's Last Exam3.6#326
AA Omniscience Index-29.3#150
CritPt (physics)0#182
AA Intelligence Index 4.3.2≈5.1#322
AA Omniscience · Accuracy0.9#323
GPQA Diamond22.4#315
AIME 2025 · AA archived2.3#136
Coding
LiveCodeBench · AA archived0.3#153
Agents & Tool Use
τ²-bench · AA9.1#229
Writing & Language
IFBench (instructions)12.1#248
FAQ
How much does Gemma 3 270M cost?›
There is no per-unit API price: self-host only.
Is Gemma 3 270M free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Gemma 3 270M, and what is it best at?›
#323 of 336 in Chat & Knowledge, #210 of 239 in Coding, #226 of 242 in Agents & Tool Use, #245 of 245 in Writing & Language.
Is Gemma 3 270M better than MiMo v2 Pro?›
On AA Omniscience · Hallucination Rate, Gemma 3 270M scores 30.4 vs 30 — about the same.
What is the context window of Gemma 3 270M?›
32K tokens.
When was Gemma 3 270M released? Is there a newer version?›
Released 2025-08-14. It is the current version in its line.
Is Gemma 3 270M open source?›
Yes, the weights are open (gemma licence).
Can I run Gemma 3 270M locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Gemma 3 270M read images?›
No, it accepts text only.
What is Gemma 3 270M?›
Gemma 3 270M is an open-weights language model from Google, released Aug 2025.
What are the best alternatives to Gemma 3 270M?›
Granite 4.2 3B (better), MiniCPM5 1B (open weights).