← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
1k
tokens
718.5
PP tok/s
44.1
TG tok/s
1425
TTFT (ms)
16.7
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 718.5 | 44.1 | 16.7 GB | current |
| 4k | 697.8 | 40.3 | 18.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 44.1 | 1.00× |
| 2× | 46.5 | 1.05× |
| 4× | 54.7 | 1.24× |