Gemma 3 270M
Gemma 3 270M is Google's language model. An ultra-compact 270-million-parameter Gemma 3 LLM for highly constrained edge deployments.
| Benchmarks | |
|---|---|
| Intelligence Index | #523 |
| Math Index | #264 |
| MMLU-Pro | #341 |
| GPQA | #532 |
| HLE | #504 |
| LiveCodeBench | #335 |
| IFBench | #426 |
| Time to First Token | #144 |
| SciCode | #531 |
| AIME 2025 | #264 |
| LCR | #447 |
| TerminalBench Hard | #385 |
| TAU2 | #390 |
| Output TPS | #378 |
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Cheapest Instances to Run It
Cloud GPU instances that can host Gemma 3 270M, ranked by cheapest on-demand price. The model needs about 1 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region | |
|---|---|---|---|---|---|---|
| g6f.large |  AWS | L4 | 3 GB | $0.202/hr | ||
| Standard_NV4as_v4 |  Azure | AMD Radeon Instinct MI25 | 16 GB | $0.233/hr | ||
| g6f.xlarge | AWS | L4 | 3 GB | $0.237/hr | ||
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Gemma 4 31B | — | — | — | — | Available |
| Gemma 4 26B A4B | — | — | — | — | Available |
| Gemma 4 31B | — | 256K | $0.140 | $0.400 | Available |
| Gemma 4 26B A4B | — | 256K | $0.130 | $0.400 | Available |
| Gemma 4 12B | — | — | — | — | Available |
| Gemma 4 E4B | — | — | — | — | Available |
| Gemma 4 E4B | — | — | — | — | Available |
| Gemma 4 E2B | — | 128K | $0.040 | $0.080 | Available |
| Gemma 4 | — | — | — | — | Available |
| Gemma 4 E2B | — | — | — | — | Available |
| Gemma 3 270M | — | — | — | — | Current |