← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
8k
tokens
59.3
PP tok/s
10.5
TG tok/s
138030
TTFT (ms)
18.7
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.9
macOS
macOS 26.4
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 62.5 | 10.4 | 16.7 GB | view |
| 4k | 62.7 | 10.7 | 18.1 GB | view |
| 8k | 59.3 | 10.5 | 18.7 GB | current |
| 16k | 56.6 | 9.8 | 20.0 GB | view |
| 32k | 52.9 | 8.0 | 22.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 10.4 | 1.00× |
| 2× | 12.2 | 1.17× |