← Back to community benchmarks
gemma-3-4b-it-qat
Performance
8k
tokens
443.0
PP tok/s
32.8
TG tok/s
18493
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.11
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 453.1 | 26.9 | 3.5 GB | view |
| 4k | 445.4 | 38.0 | 3.8 GB | view |
| 8k | 443.0 | 32.8 | 3.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 26.9 | 1.00× |
| 2× | 37.0 | 1.38× |
| 4× | 47.9 | 1.78× |
| 8× | 50.3 | 1.87× |