← Back to community benchmarks
Qwen3.5-27B
Performance
1k
tokens
463.2
PP tok/s
18.0
TG tok/s
2211
TTFT (ms)
16.7
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.18
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 463.2 | 18.0 | 16.7 GB | current |
| 4k | 476.3 | 17.3 | 18.3 GB | view |
| 8k | 446.9 | 16.0 | 18.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.0 | 1.00× |
| 2× | 29.6 | 1.64× |
| 4× | 42.8 | 2.38× |