← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
8k
tokens
182.8
PP tok/s
26.8
TG tok/s
44806
TTFT (ms)
19.2
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.3.9rc1
macOS
macOS 26.3
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 229.4 | 28.0 | 16.7 GB | view |
| 4k | 182.7 | 29.7 | 18.2 GB | view |
| 8k | 182.8 | 26.8 | 19.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 28.0 | 1.00× |
| 2× | 34.0 | 1.21× |
| 4× | 38.7 | 1.38× |