← Back to community benchmarks
Qwen_Qwen3.6-27B-oQ8-fp16-mtp
Performance
1k
tokens
142.4
PP tok/s
11.3
TG tok/s
7191
TTFT (ms)
28.3
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 142.4 | 11.3 | 28.3 GB | current |
| 4k | 147.7 | 11.1 | 29.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 11.3 | 1.00× |
| 2× | 19.3 | 1.71× |
| 4× | 22.4 | 1.98× |