← Back to community benchmarks
Qwen3.6-27B-oQ4-fp16-mtp
Performance
16k
tokens
84.9
PP tok/s
9.5
TG tok/s
192920
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.9
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 97.2 | 14.6 | 16.4 GB | view |
| 4k | 105.4 | 14.8 | 17.9 GB | view |
| 8k | 100.5 | 13.2 | 18.9 GB | view |
| 16k | 84.9 | 9.5 | 20.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 14.6 | 1.00× |
| 2× | 14.4 | 0.99× |
| 4× | 16.7 | 1.14× |
| 8× | 19.2 | 1.32× |