← Back to community benchmarks
gemma-4-31B-it
Performance
8k
tokens
94.2
PP tok/s
9.7
TG tok/s
86965
TTFT (ms)
35.0
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
64 GB
GPU Cores
38
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 94.1 | 9.9 | 31.8 GB | view |
| 4k | 94.6 | 9.9 | 34.5 GB | view |
| 8k | 94.2 | 9.7 | 35.0 GB | current |
| 16k | 92.0 | 9.1 | 36.1 GB | view |
| 32k | 83.7 | 8.2 | 39.2 GB | view |
| 64k | 75.8 | 7.0 | 45.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 9.9 | 1.00× |
| 2× | 17.9 | 1.81× |
| 4× | 22.2 | 2.24× |
| 8× | 19.0 | 1.92× |