Gemma 3n E4B Instruct
Jun 2025
Gemma 3n E4B InstructCompare inon
Gemma 3n E4B Instruct measured on 22 of 104 Chat & Knowledge benchmarks22
BenchmarkByScoreRank
Overall1
Knowledge17
Science2
Legacy · saturated or no longer reported2
No benchmark matches
—per task?
self-host onlyprice
—output speed?
32Kcontext
Alternatives?
ModelScoreCostPer taskWhat changes
BetterGPT-6 Lunalow×4.5—$0.005Function calling only with none · Chat Completions+3IOpenK2 Horizon 7Bthinking×4.1—$0.30 / $1.20Memory (4-bit): 3.9 GB → 4.5 GB+1
BetterGranite 4.2 3BthinkingOpen+47%—$0.006No image inputBetterGPT-5.6 Lunalow×4.4—$0.01BetterGPT OSS 20BhighOpen×2.4—$0.011Memory (4-bit): 3.9 GB → 13 GB+1ModelScoreCostPer 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+47%—$0.006No image inputGPT-5.6 Lunalow×4.4—$0.01GPT OSS 20BhighOpen×2.4—$0.011Memory (4-bit): 3.9 GB → 13 GB+1
Mistral Small 4thinkingOpen×2.2—$0.015Memory (4-bit): 3.9 GB → 72 GBModelScoreCostPer taskWhat changes
IK2 Horizon 7BthinkingOpen×4.1—$0.30 / $1.20Memory (4-bit): 3.9 GB → 4.5 GB+1Gemma 4 12BthinkingOpen×3.5—$0.10 / $0.30Memory (4-bit): 3.9 GB → 6 GB
Qwen 3.5 9BthinkingOpen×3.3—$0.21Memory (4-bit): 3.9 GB → 4.8 GBIK2 Horizon 3.7BthinkingOpen×3.1—$0.30 / $1.20No image inputSApriel v1.5 15B ThinkerOpen×2.7——Memory (4-bit): 3.9 GB → 7.4 GBModelScoreCostPer taskWhat changes
Gemini 4 Argonhigh×12.7—*$1.99Synchronous output stops at 65,536+2Gemini 3.1 Pro Previewthinking×10.5—$1.30Cannot use both thinking controlsGemini 3.8 Flashmedium×9.4—*$0.93Sampling parameters are ignored+1Gemini 3.6 Flashhigh×9.1—*$1.60Gemma 4 31BthinkingOpen×5.3—$0.10 / $0.34Memory (4-bit): 3.9 GB → 19 GBGemini 2.5 Prothinking×5—$0.33Gemini 2.5 Pro Preview (May' 25)thinking×4.4——No image inputGemma 4 26B A4BthinkingOpen×4.3—$0.15 / $0.60Memory (4-bit): 3.9 GB → 15 GBAll 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
in Chat & KnowledgeAA Intelligence Index 4.3.2≈4.8#327
AA Omniscience Index-81.3#317
Humanity's Last Exam4.5#295
GPQA Diamond29.6#300
IFBench (instructions)27.9#219
CritPt (physics)0#180
AIME 2025 · AA archived14.3#120
FAQ
How much does Gemma 3n E4B Instruct cost?›
There is no per-unit API price: self-host only.
Is Gemma 3n E4B Instruct free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Gemma 3n E4B Instruct, and what is it best at?›
#292 of 334 in Chat & Knowledge, #181 of 239 in Coding, #228 of 242 in Agents & Tool Use, #131 of 195 in Writing & Language, #123 of 124 in Vision & Documents.
Is Gemma 3n E4B Instruct better than G9v3 3B?›
On Humanity's Last Exam, Gemma 3n E4B Instruct scores 4.5 vs 4.5 — about the same.
What is the context window of Gemma 3n E4B Instruct?›
32K tokens.
When was Gemma 3n E4B Instruct released? Is there a newer version?›
Released 2025-06-26. It has been superseded by Gemma 4 E4B.
Is Gemma 3n E4B Instruct open source?›
Yes, the weights are open (gemma licence).
Can I run Gemma 3n E4B Instruct locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Gemma 3n E4B Instruct read images?›
It accepts text and images as input.
What is Gemma 3n E4B Instruct?›
Gemma 3n E4B Instruct is an open-weights language model from Google, released Jun 2025.
What are the best alternatives to Gemma 3n E4B Instruct?›
GPT-6 Luna (better), K2 Horizon 7B (open weights).