← Back to community benchmarks
gemma-4-31B-it-oQ4
Performance
16k
tokens
191.1
PP tok/s
20.7
TG tok/s
85745
TTFT (ms)
23.8
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev1
macOS
macOS 15.7.4
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 199.1 | 23.4 | 18.1 GB | view |
| 4k | 200.8 | 22.8 | 20.3 GB | view |
| 8k | 197.9 | 22.1 | 22.6 GB | view |
| 16k | 191.1 | 20.7 | 23.8 GB | current |
| 32k | 178.9 | 18.7 | 25.4 GB | view |
| 64k | 157.8 | 15.5 | 31.4 GB | view |
| 128k | 123.4 | 11.6 | 43.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 23.4 | 1.00× |
| 2× | 37.6 | 1.61× |
| 4× | 42.2 | 1.80× |