Gemma 4 E2B
Gemma 4 E2BAlternatives?
CheaperLing 3.0 Flash VLthinkingOpen+77%-44%$0.06 / $0.18Memory (4-bit): 2.6 GB → 75 GB
BetterGPT-6 Lunalow+70%+25%$0.005Function calling only with none · Chat Completions+3OpenGemma 4 12Bthinking+56%-6%$0.10 / $0.30Memory (4-bit): 2.6 GB → 6 GB
CheaperAgnes 2.5 Pro Beta+69%-6%$0.10 / $0.30
CheaperQwen 3.5 9BthinkingOpen+55%-42%$0.21Memory (4-bit): 2.6 GB → 4.8 GBLing 3.0 Flash VLthinkingOpen+77%-44%$0.06 / $0.18Memory (4-bit): 2.6 GB → 75 GBAgnes 2.5 Pro Beta+69%-6%$0.10 / $0.30Gemma 4 12BthinkingOpen+56%-6%$0.10 / $0.30Memory (4-bit): 2.6 GB → 6 GBQwen 3.5 9BthinkingOpen+55%-42%$0.21Memory (4-bit): 2.6 GB → 4.8 GBDiffusionGemma 26B A4BOpen+49%-53%$0.05 / $0.15Memory (4-bit): 2.6 GB → 15 GBGPT-6 Lunalow+70%+25%$0.005Function calling only with none · Chat Completions+3Gemma 4 E4BthinkingOpen+15%-75%$0.008Memory (4-bit): 2.6 GB → 4 GBGPT-5.6 Lunalow+66%+181%$0.01
Mistral Small 4thinkingOpen+27%+64%$0.015Memory (4-bit): 2.6 GB → 72 GB
MiMo v2.5thinkingOpen+69%+9%$0.019Memory (4-bit): 2.6 GB → 186 GBGemma 4 12BthinkingOpen+56%-6%$0.10 / $0.30Memory (4-bit): 2.6 GB → 6 GBQwen 3.5 9BthinkingOpen+55%-42%$0.21Memory (4-bit): 2.6 GB → 4.8 GBQwen3.5 4BthinkingOpen+47%-63%$0.03 / $0.15
Step3 VL 10BOpen+44%——Context: 128K → 66K+1Qwen3 VL 8B (Reasoning)thinkingOpen+27%+311%$0.18 / $2.09Memory (4-bit): 2.6 GB → 4.4 GBGemini 3.8 Flashmedium+89%—*$0.93Sampling parameters are ignored+1Gemini 3.6 Flashhigh+87%—*$1.60Gemini 3.1 Pro Previewthinking+85%—$1.30Cannot use both thinking controlsGemini 3.5 Flash Litehigh+77%—$0.19Gemini 3 Flash Previewnon-thinking+76%—$0.50 / $3Gemini 3.1 Flash Litehigh+70%—$0.06Gemini 2.5 Prothinking+68%—$0.33Gemma 4 31BthinkingOpen+65%—$0.10 / $0.34Memory (4-bit): 2.6 GB → 19 GBAll Google models →Run it yourself
estimateBenchmarks
in Vision & DocumentsFAQ
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 Ministral 3 8B 2512?›
On MMMU-Pro (vision), Gemma 4 E2B scores 44.6 vs 46 — lower.
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?›
Ling 3.0 Flash VL (cheaper), GPT-6 Luna (better), Gemma 4 12B (open weights).