Gemma 3 4B
GoogleReleased Mar 12, 2025Open weights · Gemma Terms of Usegemma-3-4b
- Intelligence (Epoch)
- 116 · 111th of 111
- Reasoning
- no
- Knowledge cutoff
- January 2025
- Context
- 128k tokens
- Max output
- 16k tokens
- Input
- text, image
- API features
- structured outputs, JSON mode, seed, logprobs
Read Oct 23, 06:00 UTC from the hosts' published offers and OpenRouter, spec sheet from Google · cutoff: ai.google.dev
Intelligence for the price
1 model scores higher for the same price or less; it ranks 2 of the 3 models at its price or below.
Epoch Capabilities Index against the lowest input + output price per M, log scale · prices Oct 23. Score: Epoch AI, CC BY 4.0, 116 with an interval of 97 to 124.
Against its rivals
The best of its price range and the top score
- Gemma 3 4Bthis model$0.09116
- Claude Opus 5.5top score$24.00169
- Qwen3.7 Flashsame price range$0.16144
- gpt-oss-120bsame price range$0.18140
Same level for 2.4× less: Mistral Nemo at Io Net, $0.038 per M input + output · their Epoch intervals overlap (119 against 116).
Bars: Epoch Capabilities Index (Epoch AI, CC BY 4.0), drawn from 100, below the lowest score in the catalogue · price: lowest input + output per M.
Open weights under Gemma Terms of Use: you can run Gemma 3 4B on your own hardware instead of paying per token.
Memory ≈ parameters × bytes per parameter × 1.2 · cloud price: on-demand rate, running 24/7 · builds: GGUF, AWQ, MLX, GPTQ, Ollama · break-even calculator
| Provider | Input | Output | Cache ↑ | tok/s | First token | Uptime 24h | Checked |
|---|---|---|---|---|---|---|---|
| Parasailbf16 · 128K ctx | $0.04 | $0.05 | $0.02 | 123 | 0.79 s | 100% | Oct 23 |
| DeepInfrabf16 · 128K ctx · 16K out | $0.05 | $0.10 | — | 74 | 0.70 s | 100% | Oct 23 |
2 of 2 providers · prices per million tokens, read Oct 23, 06:00 UTC · speed: OpenRouter, median of the last 30 min, read Oct 23, 06:00 UTC · uptime: OpenRouter, last 24 h · under each host: weights precision, context and max output as served, the maker's value in brackets when the host's differs
| Provider | Weights | Context | Max output | Tools | Structured outputs | Reasoning |
|---|---|---|---|---|---|---|
| Parasail | bf16 | 128K | not read: host terms | no | yes | no |
| DeepInfra | bf16 | 128K | 16K | no | yes | no |
Weights, context and max output: read at each host's own catalogue or docs where its terms allow, otherwise as the host declares to OpenRouter; hover a cell for its source and date · tools, structured outputs, reasoning: as declared to OpenRouter · not verified by us
Gemma 3 4B spec sheet, field by field, with sources
Gemma 3 4B spec sheetmaker-declared
What Google declares about the model itself — read from its own weights repository and documentation, not from any host. What each endpoint actually serves is in the pricing above: the two can differ, and both are true.
- Context window
- weights repository under access conditions
- Parameters
- weights repository under access conditions
- Active experts
- weights repository under access conditions
- Weight precision
- weights repository under access conditions
- License
- Gemma Terms of Use — open weights, conditionalcuratedScope: the licence on the published weights, and nothing else. It is not the maker's acceptable-use policy, which is a separate document, and it is not the contract you sign with whichever host you call — hosts set their own terms, which this index does not read.
- Knowledge cutoff
- January 2025maker's docs
- Modalities
- weights repository under access conditions
- Max output (official)
- to verify
- Release date
- to verify≈ March 12, 2025 third-party catalogue — not the maker's figure
- Maker lifecycle status
- to verify
google/gemma-3-4b-it · weights repository @ 093f9f3 · file not readable · read 2026-10-08 · 2 of 10 fields published by the maker
| Provider | Chatbot 1,000 in / 500 out | RAG / long context 8,000 in / 500 out | Batch summarize 4,000 in / 1,000 out |
|---|---|---|---|
| Parasail | $0.06 | $0.34 | $0.21 |
| DeepInfra | $0.10 | $0.45 | $0.30 |
What each host bills for 1,000 requests of a representative job
Your own workload
Other Google models · all its models, hosts and history ›
- Gemma 4 31B14 providers · from $0.38
- Gemma 4 26B A4B12 providers · from $0.26
- Gemma 3 27B5 providers · from $0.24
- Gemma 3 12B3 providers · from $0.15
- Gemini 2.5 Flash1 provider · from $2.80
- Gemini 2.5 Pro1 provider · from $11.25