← Back to community benchmarks
gemma-4-31b-mxfp8-converted
Performance
4k
tokens
553.0
PP tok/s
13.8
TG tok/s
7409
TTFT (ms)
32.8
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.4
macOS
macOS 26.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 581.4 | 15.0 | 31.2 GB | view |
| 4k | 553.0 | 13.8 | 32.8 GB | current |
| 8k | 518.9 | 12.1 | 33.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 15.0 | 1.00× |
| 2× | 20.2 | 1.35× |
| 4× | 23.5 | 1.57× |