← Back to community benchmarks
Qwen3.6-27B-oQ8-fp16-mtp
Performance
8k
tokens
148.1
PP tok/s
16.3
TG tok/s
55330
TTFT (ms)
31.3
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 143.8 | 17.0 | 28.8 GB | view |
| 4k | 148.8 | 17.0 | 30.3 GB | view |
| 8k | 148.1 | 16.3 | 31.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 17.0 | 1.00× |
| 2× | 20.2 | 1.19× |
| 4× | 22.5 | 1.32× |