← Back to community benchmarks
gemma-4-31B-it-oQ6
Performance
64k
tokens
447.3
PP tok/s
11.7
TG tok/s
146531
TTFT (ms)
35.2
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.12
macOS
macOS 26.5
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 556.6 | 17.7 | 25.3 GB | view |
| 64k | 447.3 | 11.7 | 35.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 17.7 | 1.00× |
| 2× | 27.3 | 1.54× |