← Back to community benchmarks
Qwen3.6-27B-oQ4-fp16-mtp
Performance
32k
tokens
617.9
PP tok/s
32.3
TG tok/s
53032
TTFT (ms)
22.5
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9
macOS
macOS 26.4.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 744.7 | 46.3 | 16.7 GB | view |
| 4k | 741.2 | 45.1 | 18.2 GB | view |
| 32k | 617.9 | 32.3 | 22.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 46.3 | 1.00× |
| 2× | 45.8 | 0.99× |