Gemma 4 E2B
Gemma 4 E2BAlternatives?
CheaperAgnes 2.5 Pro Beta×7.9-6%$0.10 / $0.30
BetterGPT-6 Lunalow×4.2+25%$0.005Function calling only with none · Chat Completions+3IOpenK2 Horizon 7Bthinking×3.8+228%$0.30 / $1.20Memory (4-bit): 2.6 GB → 4.5 GB+1
CheaperSolar Mini 4×5.4-45%$0.37No image input
CheaperLing 3.0 FlashthinkingOpen×5-44%$0.06 / $0.18Memory (4-bit): 2.6 GB → 76 GB+1Agnes 2.5 Pro Beta×7.9-6%$0.10 / $0.30Solar Mini 4×5.4-45%$0.37No image inputLing 3.0 FlashthinkingOpen×5-44%$0.06 / $0.18Memory (4-bit): 2.6 GB → 76 GB+1Ling 3.0 Flash FinthinkingOpen×4.7-44%$0.06 / $0.18Memory (4-bit): 2.6 GB → 76 GB+1Ling 3.0 Flash VLthinkingOpen×4.6-44%$0.06 / $0.18Memory (4-bit): 2.6 GB → 75 GBGPT-6 Lunalow×4.2+25%$0.005Function calling only with none · Chat Completions+3GPT-5.6 Lunalow×4.2+181%$0.01GPT OSS 20BhighOpen×2.3-78%$0.011Memory (4-bit): 2.6 GB → 13 GB+1
Mistral Small 4thinkingOpen×2.1+64%$0.015Memory (4-bit): 2.6 GB → 72 GB
Nemotron 3 Nano 30B A3BthinkingOpen×2.4-34%$0.017Memory (4-bit): 2.6 GB → 19 GB+1Gemma 4 12BthinkingOpen×3.3-6%$0.10 / $0.30Memory (4-bit): 2.6 GB → 6 GB
Qwen 3.5 9BthinkingOpen×3.1-42%$0.21Memory (4-bit): 2.6 GB → 4.8 GBIK2 Horizon 3.7BthinkingOpen×2.9+228%$0.30 / $1.20No image inputTFalcon H1R 7BthinkingOpen×2.3——Memory (4-bit): 2.6 GB → 3.8 GB+1Gemini 4 Argonhigh×12—*$1.99Synchronous output stops at 65,536+2Gemini 3.1 Pro Previewthinking×9.9—$1.30Cannot use both thinking controlsGemini 3.8 Flashmedium×8.8—*$0.93Sampling parameters are ignored+1Gemini 3.6 Flashhigh×8.6—*$1.60Gemma 4 31BthinkingOpen×5—$0.10 / $0.34Memory (4-bit): 2.6 GB → 19 GBGemini 2.5 Prothinking×4.7—$0.33Gemini 2.5 Pro Preview (May' 25)thinking×4.2——No image inputGemma 4 26B A4BthinkingOpen×4—$0.15 / $0.60Memory (4-bit): 2.6 GB → 15 GBAll Google models →Run it yourself
estimateBenchmarks
in Chat & KnowledgeFAQ
How much does Gemma 4 E2B cost?›
$0.08 per 1M input tokens and $0.40 per 1M output tokens (cheapest host: Featherless).
Is Gemma 4 E2B free to use?›
There is no free API; the cheapest paid price is $0.08 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Gemma 4 E2B, and what is it best at?›
#286 of 334 in Chat & Knowledge, #177 of 239 in Coding, #122 of 175 in Agents & Tool Use, #167 of 245 in Writing & Language, #115 of 124 in Vision & Documents.
Is Gemma 4 E2B better than Gemma 3n E2B Instruct?›
On Humanity's Last Exam, Gemma 4 E2B scores 4.8 vs 4.2 — about the same.
How can I use Gemma 4 E2B?›
Through the API of Featherless.
What is the context window of Gemma 4 E2B?›
128K tokens.
When was Gemma 4 E2B released? Is there a newer version?›
Released 2026-04-02. It is the current version in its line.
Is Gemma 4 E2B open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Gemma 4 E2B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Gemma 4 E2B read images?›
It accepts text and images, audio as input.
What is Gemma 4 E2B?›
Gemma 4 E2B is an open-weights language model from Google, released Apr 2026, the successor to Gemma 3n E2B Instruct.
What are the best alternatives to Gemma 4 E2B?›
Agnes 2.5 Pro Beta (cheaper), GPT-6 Luna (better), K2 Horizon 7B (open weights).