Gemma 3n E4B Instruct
Jun 2025
Gemma 3n E4B InstructCompare inon
Gemma 3n E4B Instruct measured on 24 of 109 Chat & Knowledge benchmarks24
BenchmarkByScoreRank
Overall1
Knowledge18
Science2
Documents1
Legacy · saturated or no longer reported2
No benchmark matches
—per task?
self-host onlyprice
—output speed?
32Kcontext
Alternatives?
ModelScoreCostPer taskWhat changes
BetterGPT-5 Minihighwins 61%—$0.053
OpenGranite 4.2 8Bunstatedwins 58%—$0.06 / $0.25Memory (4-bit): 3.9 GB → 4.4 GB+1BetterGPT-6 Lunamaxwins 66%—$0.068Function calling only with none · Chat Completions+3
BetterClaude Haiku 5.5highwins 67%—$0.079Remove sampling parameters+5BetterGPT-5.6 Lunaxhighwins 72%—$0.085ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
GPT-5 Minihighwins 61%—$0.053GPT-6 Lunamaxwins 66%—$0.068Function calling only with none · Chat Completions+3Claude Haiku 5.5highwins 67%—$0.079Remove sampling parameters+5GPT-5.6 Lunaxhighwins 72%—$0.085GPT-5.6 Terraxhighwins 77%—$0.63Prompts with >272K input tokensModelScoreCostPer taskWhat changes
Granite 4.2 8BunstatedOpenwins 58%—$0.06 / $0.25Memory (4-bit): 3.9 GB → 4.4 GB+1
NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4Openwins 58%——Memory (4-bit): 3.9 GB → 11 GB+1Granite 4.1 8BunstatedOpenwins 54%——Memory (4-bit): 3.9 GB → 4.4 GB+1Granite 4.2 3BunstatedOpenwins 45%—$0.03 / $0.12No image input
GLM-4Openwins 39%——Context: not verified+2ModelScoreCostPer taskWhat changes
Gemini 4 Argonhighwins 84%—*$1.62Synchronous output stops at 65,536+2Gemini 3.8 Flashhighwins 80%—*$3.49Sampling parameters are ignored+1Gemini 3.6 Flashhighwins 78%—*$1.60Gemini 3.1 Pro Previewunstatedwins 78%—$2 / $12Cannot use both thinking controlsGemini 3 Flash Previewunstatedwins 76%—$0.50 / $3Gemini 2.5 Prounstatedwins 76%—$1.25 / $10Gemma 4 26B A4BunstatedOpenwins 75%—$0.15 / $0.60Memory (4-bit): 3.9 GB → 15 GBGemma 4 31BunstatedOpenwins 72%—$0.10 / $0.34Memory (4-bit): 3.9 GB → 19 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#329
AA Omniscience Index-81.3#319
Humanity's Last Exam4.5#297
GPQA Diamond29.6#300
IFBench (instructions)27.9#219
CritPt (physics)0#182
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?›
#294 of 336 in Chat & Knowledge, #181 of 239 in Coding, #228 of 242 in Agents & Tool Use, #136 of 197 in Writing & Language, #124 of 125 in Vision & Documents.
Is Gemma 3n E4B Instruct better than GPT OSS 20B?›
On Arena Text · Chinese, Gemma 3n E4B Instruct scores 1,308.8 vs 1,314.5 — 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-5 Mini (better), Granite 4.2 8B (open weights).