← Back to community benchmarks
gemma-4-31B-it-Claude-Opus-Distill
Performance
1k
tokens
663.8
PP tok/s
26.0
TG tok/s
1543
TTFT (ms)
17.6
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.4
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 663.8 | 26.0 | 17.6 GB | current |
| 4k | 614.1 | 23.5 | 19.4 GB | view |
| 8k | 570.3 | 20.1 | 19.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 26.0 | 1.00× |
| 2× | 36.7 | 1.41× |
| 4× | 43.2 | 1.66× |