← Back to community benchmarks
Qwen3.6-27B-oQ8-mtp
Performance
8k
tokens
212.3
PP tok/s
24.5
TG tok/s
38588
TTFT (ms)
31.3
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.3.9
macOS
macOS 26.3
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 236.9 | 27.1 | 28.8 GB | view |
| 4k | 237.3 | 26.3 | 30.3 GB | view |
| 8k | 212.3 | 24.5 | 31.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 27.1 | 1.00× |
| 2× | 30.2 | 1.11× |
| 4× | 34.7 | 1.28× |