← Back to community benchmarks
gemma-3-4b-it-qat
Performance
16k
tokens
477.5
PP tok/s
54.7
TG tok/s
34317
TTFT (ms)
4.3
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
32 GB
GPU Cores
24
Software
oMLX
v0.2.12
macOS
macOS 26.2
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 493.5 | 73.4 | 3.6 GB | view |
| 4k | 487.6 | 69.5 | 3.8 GB | view |
| 8k | 484.0 | 64.5 | 4.0 GB | view |
| 16k | 477.5 | 54.7 | 4.3 GB | current |
| 32k | 462.8 | 38.8 | 4.8 GB | view |
| 64k | 431.3 | 18.6 | 6.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 73.4 | 1.00× |
| 2× | 88.3 | 1.20× |
| 4× | 93.3 | 1.27× |