← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
16k
tokens
61.5
PP tok/s
11.0
TG tok/s
266545
TTFT (ms)
20.7
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
32 GB
GPU Cores
24
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 62.0 | 12.4 | 16.8 GB | view |
| 4k | 63.5 | 12.2 | 18.2 GB | view |
| 8k | 63.0 | 11.9 | 19.2 GB | view |
| 16k | 61.5 | 11.0 | 20.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 12.4 | 1.00× |
| 2× | 13.6 | 1.10× |
| 4× | 15.5 | 1.25× |
| 8× | 14.4 | 1.16× |