← Back to community benchmarks
gemma-4-31B-it-oQ4
Performance
64k
tokens
494.8
PP tok/s
15.1
TG tok/s
132449
TTFT (ms)
28.0
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 | 675.5 | 25.8 | 18.1 GB | view |
| 64k | 494.8 | 15.1 | 28.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 25.8 | 1.00× |
| 2× | 41.3 | 1.60× |