Model benchmarks
gemma4:31b local LLM performance
As of May 2026, gemma4:31b runs at up to 7.5 tok/s for local inference (best of 10 community benchmark runs across 2 GPUs).
OllamaQ4_K_M
Model size
31.3B
Peak speed
7.5 tok/s
Average speed
5.3 tok/s
Min memory
23.2 GB
Max context
5,409 tokens
Best quality
92.8
Benchmark runs
10
GPUs tested
2
Performance by hardware and tool
Every hardware/tool/quantization combination gemma4:31b has been benchmarked on, ranked by peak token generation speed. Last updated May 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| Apple M5 Max | Ollama | Q4_K_M | 7.5 tok/s | 7.4 tok/s | 28.4 GB | 5,073 tokens | 76.0 | 2 |
| AMD Radeon RX 7900 XTX | Ollama | Q4_K_M | 7.1 tok/s | 4.8 tok/s | 23.2 GB | 5,409 tokens | 66.2 | 8 |
Frequently asked questions
- How fast is gemma4:31b for local inference?
- Across 10 community benchmark runs, gemma4:31b reaches up to 7.5 tok/s and averages 5.3 tok/s, with the fastest results on Apple M5 Max.
- How much memory does gemma4:31b need?
- The leanest observed configuration used about 23.2 GB of memory (quantizations tested: Q4_K_M).
- Which tools have been used to run gemma4:31b?
- Benchmarks were submitted using Ollama. Results are community-contributed and updated as new runs arrive.