← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
16k
tokens
148.2
PP tok/s
6.0
TG tok/s
110554
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.4.4rc2
macOS
macOS 15.7.7
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 237.8 | 28.4 | 16.4 GB | view |
| 4k | 212.4 | 24.3 | 17.9 GB | view |
| 8k | 193.5 | 26.1 | 18.9 GB | view |
| 16k | 148.2 | 6.0 | 20.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 28.4 | 1.00× |
| 2× | 16.0 | 0.56× |