← Back to community benchmarks
Qwen3.6-27B-oQ8-mtp
Performance
1k
tokens
104.2
PP tok/s
17.7
TG tok/s
9829
TTFT (ms)
28.8
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
96 GB
GPU Cores
38
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 | 104.2 | 17.7 | 28.8 GB | current |
| 4k | 110.5 | 17.7 | 30.3 GB | view |
| 8k | 111.0 | 17.2 | 31.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 17.7 | 1.00× |
| 2× | 21.3 | 1.20× |
| 4× | 27.8 | 1.57× |