← Back to community benchmarks
Qwen3.6-27B-oQ4-fp16-mtp
Performance
4k
tokens
910.3
PP tok/s
47.3
TG tok/s
4499
TTFT (ms)
18.2
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9rc1
macOS
macOS 26.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 765.7 | 46.6 | 16.7 GB | view |
| 4k | 910.3 | 47.3 | 18.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 46.6 | 1.00× |
| 2× | 56.7 | 1.22× |
| 4× | 71.5 | 1.53× |