← Back to community benchmarks
Qwen3.6-27B
Performance
8k
tokens
421.3
PP tok/s
12.5
TG tok/s
19445
TTFT (ms)
24.6
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.4.4
macOS
macOS 26.5.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 392.8 | 12.8 | 22.1 GB | view |
| 4k | 436.8 | 12.7 | 23.5 GB | view |
| 8k | 421.3 | 12.5 | 24.6 GB | current |
| 16k | 405.9 | 12.2 | 26.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 12.8 | 1.00× |
| 2× | 22.0 | 1.72× |
| 4× | 26.6 | 2.08× |