← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
1k
tokens
234.7
PP tok/s
40.2
TG tok/s
4362
TTFT (ms)
16.7
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.3.9rc1
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 234.7 | 40.2 | 16.7 GB | current |
| 4k | 239.9 | 38.1 | 18.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 40.2 | 1.00× |
| 2× | 47.8 | 1.19× |
| 4× | 54.0 | 1.34× |