← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
8k
tokens
83.6
PP tok/s
14.1
TG tok/s
98010
TTFT (ms)
18.9
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.9
macOS
macOS 26.5
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 87.6 | 17.8 | 16.4 GB | view |
| 4k | 86.1 | 17.1 | 17.9 GB | view |
| 8k | 83.6 | 14.1 | 18.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 17.8 | 1.00× |
| 2× | 18.5 | 1.04× |
| 4× | 19.8 | 1.11× |