← Back to community benchmarks
Qwen3.6-27B-oQ4-fp16-mtp
Performance
1k
tokens
222.5
PP tok/s
30.3
TG tok/s
4603
TTFT (ms)
22.4
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9rc1
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 222.5 | 30.3 | 22.4 GB | current |
| 4k | 196.9 | 25.7 | 23.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 30.3 | 1.00× |
| 2× | 27.2 | 0.90× |
| 4× | 35.3 | 1.17× |