← Back to community benchmarks
Qwen3.5-27B
Performance
1k
tokens
100.9
PP tok/s
15.3
TG tok/s
10147
TTFT (ms)
16.6
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
48 GB
GPU Cores
16
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 100.9 | 15.3 | 16.6 GB | current |
| 4k | 101.3 | 15.0 | 17.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 15.3 | 1.00× |
| 2× | 24.8 | 1.62× |
| 4× | 26.6 | 1.74× |