Gemma 3 4B
Gemma 3 4BRankingconfiguration unstated?
Alternatives?
BetterClaude Opus 5unstated×2.5+23,429%$5 / $25OpenGemma 4 12Bunstated+42%+253%$0.10 / $0.30Memory (4-bit): 2.2 GB → 6 GBBetterClaude Fable 5.1unstated×2.5+46,959%$10 / $50Replace forced tool_choice+5BetterClaude Opus 5.5unstated×2.5+18,724%$4 / $20No forced tool use+5BetterClaude Fable 5unstated×2.4+46,959%$10 / $50Claude Opus 5unstated×2.5+23,429%$5 / $25Claude Fable 5.1unstated×2.5+46,959%$10 / $50Replace forced tool_choice+5Claude Opus 5.5unstated×2.5+18,724%$4 / $20No forced tool use+5Claude Fable 5unstated×2.4+46,959%$10 / $50
Grok 4.7unstated×2.4+6,959%$2 / $6Reasoning cannot be disabled+4Gemma 4 12BunstatedOpen+42%+253%$0.10 / $0.30Memory (4-bit): 2.2 GB → 6 GBGemma 3 12BunstatedOpen+22%+47%$0.05 / $0.10Memory (4-bit): 2.2 GB → 6.1 GBNNanbeige4 3B Thinking 2511Open-8%——Context: 131K → 66K+1
Mistral NemounstatedOpen-17%+253%$0.15 / $0.15Memory (4-bit): 2.2 GB → 6.1 GB+1
Qwen3 4BunstatedOpen-51%+1,076%$0.40 / $0.80Context: 131K → 33K+1Gemini 4 Argonunstated×2.4—*$2 / $10Synchronous output stops at 65,536+2Gemini 3.8 Flashunstated×2.2—*$0.75 / $3.75Sampling parameters are ignored+1Gemini 3.1 Pro Previewunstated+98%—$2 / $12Cannot use both thinking controlsGemma 4 31BunstatedOpen+64%—$0.10 / $0.34Memory (4-bit): 2.2 GB → 19 GBGemini 3 Flash Previewunstated+62%—$0.50 / $3Gemma 4 26B A4BunstatedOpen+47%—$0.15 / $0.60Memory (4-bit): 2.2 GB → 15 GBGemma 4 12BunstatedOpen+42%—$0.10 / $0.30Memory (4-bit): 2.2 GB → 6 GBGemma 3 27BunstatedOpen+22%—$0.08 / $0.16Memory (4-bit): 2.2 GB → 16 GBAll Google models →Run it yourself
estimateBenchmarks
all categoriesFAQ
How much does Gemma 3 4B cost?›
$0.04 per 1M input tokens and $0.05 per 1M output tokens; cached input $0.02 per 1M (cheapest host: Parasail).
Is Gemma 3 4B free to use?›
There is no free API; the cheapest paid price is $0.04 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Gemma 3 4B, and what is it best at?›
#164 of 205 in Chat & Knowledge, #36 of 39 in Agents & Tool Use, #141 of 197 in Writing & Language, #31 of 41 in Vision & Documents.
Is Gemma 3 4B better than MiniMax M2-her?›
On EQ-Bench Longform Creative Writing 1.11, Gemma 3 4B scores 34.4 vs 34.8 — about the same.
How can I use Gemma 3 4B?›
Through the API of AWS Bedrock, DeepInfra, Parasail.
What is the context window of Gemma 3 4B?›
131K tokens, with up to 118K output tokens.
When was Gemma 3 4B released? Is there a newer version?›
Released 2025-02-20. It is the current version in its line.
Is Gemma 3 4B open source?›
Yes, the weights are open (gemma licence).
Can I run Gemma 3 4B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Gemma 3 4B read images?›
It accepts text and images as input.
What is Gemma 3 4B?›
Gemma 3 4B is an open-weights language model from Google, released Feb 2025.
What are the best alternatives to Gemma 3 4B?›
Claude Opus 5 (better), Gemma 4 12B (open weights).