← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
8k
tokens
198.8
PP tok/s
20.2
TG tok/s
41215
TTFT (ms)
18.9
Peak mem (GB)
Hardware
Chip
M4 Max (32c)
Memory
36 GB
GPU Cores
32
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 195.8 | 21.4 | 16.5 GB | view |
| 4k | 200.7 | 20.1 | 17.9 GB | view |
| 8k | 198.8 | 20.2 | 18.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 21.4 | 1.00× |
| 2× | 39.7 | 1.86× |
| 4× | 45.2 | 2.11× |