← Back to community benchmarks
gemma-3-4b-it-qat
Performance
4k
tokens
430.9
PP tok/s
39.1
TG tok/s
9508
TTFT (ms)
3.5
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 405.5 | 40.5 | 3.1 GB | view |
| 4k | 430.9 | 39.1 | 3.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 40.5 | 1.00× |
| 2× | 74.3 | 1.83× |
| 4× | 92.2 | 2.28× |