Gemma 3n E2B Instruct
Jun 2025
Gemma 3n E2B InstructCompare inon
Benchmarks of Gemma 3n E2B Instruct12
BenchmarkByScoreRank
Overall1
Knowledge4
Science2
Coding1
Legacy · saturated or no longer reported4
No benchmark matches
—per task?
self-host onlyprice
—output speed?
32Kcontext
Ranking?
Alternatives?
ModelScoreCostPer taskWhat changes
BetterGPT-6 Lunalow×4.5—$0.005Function calling only with none · Chat Completions+3IOpenK2 Horizon 7Bthinking×4.3—$0.30 / $1.20Memory (4-bit): 2.7 GB → 4.5 GB+1
BetterGranite 4.2 3BthinkingOpen+87%—$0.006No image inputBetterGemma 4 E4BthinkingOpen+84%—$0.008Memory (4-bit): 2.7 GB → 4 GBBetterGPT-5.6 Lunalow×4.3—$0.01ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
GPT-6 Lunalow×4.5—$0.005Function calling only with none · Chat Completions+3Granite 4.2 3BthinkingOpen+87%—$0.006No image inputGemma 4 E4BthinkingOpen+84%—$0.008Memory (4-bit): 2.7 GB → 4 GBGPT-5.6 Lunalow×4.3—$0.01GPT OSS 20BhighOpen+86%—$0.011Memory (4-bit): 2.7 GB → 13 GB+1ModelScoreCostPer taskWhat changes
IK2 Horizon 7BthinkingOpen×4.3—$0.30 / $1.20Memory (4-bit): 2.7 GB → 4.5 GB+1IK2 Horizon 3.7BthinkingOpen×3.2—$0.30 / $1.20No image inputGemma 4 12BthinkingOpen×2.9—$0.10 / $0.30Memory (4-bit): 2.7 GB → 6 GB
Qwen 3.5 9Bnon-thinkingOpen×2.7—$0.08 / $0.13Memory (4-bit): 2.7 GB → 4.8 GBQwen3.5 4BthinkingOpen×2.7—$0.03 / $0.15ModelScoreCostPer taskWhat changes
Gemini 4 Argonhigh×10.9—*$1.99Synchronous output stops at 65,536+2Gemini 3.8 Flashmedium×8.2—*$0.93Sampling parameters are ignored+1Gemini 3.6 Flashhigh×7—*$1.60Gemini 3.1 Pro Previewthinking×6.1—$1.30Cannot use both thinking controlsGemini 3.5 Flash Litehigh×4.6—$0.19Gemini 3 Flash Previewnon-thinking×3.7—$0.50 / $3Gemma 4 26B A4BthinkingOpen×3.4—$0.15 / $0.60Memory (4-bit): 2.7 GB → 15 GBGemini 2.5 Prothinking×3.3—$0.33All Google models →Run it yourself
estimateFits on✓ 8 GB (phone, laptop) · 8-bit✓ 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 Exam4.2#306
AA Omniscience Index-80.2#315
CritPt (physics)0#180
AA Intelligence Index 4.3.2≈4.8#327
AA Omniscience · Accuracy6.8#303
GPQA Diamond22.9#313
AIME 2025 · AA archived10.3#127
Coding
LiveCodeBench · AA archived9.5#146
Agents & Tool Use
τ²-bench · AA0#232
Writing & Language
IFBench (instructions)22#239
FAQ
How much does Gemma 3n E2B Instruct cost?›
There is no per-unit API price: self-host only.
Is Gemma 3n E2B Instruct free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Gemma 3n E2B Instruct, and what is it best at?›
#303 of 334 in Chat & Knowledge, #203 of 239 in Coding, #229 of 242 in Agents & Tool Use, #236 of 245 in Writing & Language.
Is Gemma 3n E2B Instruct better than Apertus 8B Instruct?›
On AA Intelligence Index 4.3.2, Gemma 3n E2B Instruct scores 4.8 vs 4.8 — about the same.
What is the context window of Gemma 3n E2B Instruct?›
32K tokens.
When was Gemma 3n E2B Instruct released? Is there a newer version?›
Released 2025-06-26. It has been superseded by Gemma 4 E2B.
Is Gemma 3n E2B Instruct open source?›
Yes, the weights are open (gemma licence).
Can I run Gemma 3n E2B Instruct locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Gemma 3n E2B Instruct read images?›
It accepts text and images as input.
What is Gemma 3n E2B Instruct?›
Gemma 3n E2B Instruct is an open-weights language model from Google, released Jun 2025.
What are the best alternatives to Gemma 3n E2B Instruct?›
GPT-6 Luna (better), K2 Horizon 7B (open weights).