← Back to community benchmarks
gemma-3-27b-it-qat
Performance
16k
tokens
85.3
PP tok/s
11.1
TG tok/s
192090
TTFT (ms)
18.6
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 | 87.0 | 12.3 | 16.8 GB | view |
| 4k | 86.5 | 16.0 | 17.7 GB | view |
| 8k | 86.3 | 14.3 | 18.0 GB | view |
| 16k | 85.3 | 11.1 | 18.6 GB | current |
| 32k | 82.9 | 7.3 | 19.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 12.3 | 1.00× |
| 2× | 109.9 | 8.93× |
| 4× | 133.1 | 10.82× |