← Back to community benchmarks
gemma-3-4b-it-qat
Performance
16k
tokens
638.4
PP tok/s
66.7
TG tok/s
25668
TTFT (ms)
4.3
Peak mem (GB)
Hardware
Chip
M2 Max (30c)
Memory
64 GB
GPU Cores
30
Software
oMLX
v0.2.7
macOS
macOS 15.7.4
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 662.2 | 94.8 | 3.6 GB | view |
| 4k | 655.7 | 89.2 | 3.8 GB | view |
| 8k | 649.5 | 81.5 | 4.0 GB | view |
| 16k | 638.4 | 66.7 | 4.3 GB | current |
| 32k | 617.9 | 50.1 | 4.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 94.8 | 1.00× |
| 2× | 105.8 | 1.12× |
| 4× | 1446.9 | 15.26× |