← Back to community benchmarks
Qwen3.6-27B-oQ4-fp16-mtp
Performance
1k
tokens
143.5
PP tok/s
17.7
TG tok/s
7138
TTFT (ms)
16.4
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.4.1
macOS
macOS 26.5.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 143.5 | 17.7 | 16.4 GB | current |
| 4k | 139.7 | 17.1 | 17.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 17.7 | 1.00× |
| 2× | 25.5 | 1.44× |
| 4× | 27.6 | 1.56× |