← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
32k
tokens
142.2
PP tok/s
18.7
TG tok/s
230451
TTFT (ms)
23.7
Peak mem (GB)
Hardware
Chip
M3 Max (30c)
Memory
36 GB
GPU Cores
30
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.4.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 159.2 | 25.9 | 16.8 GB | view |
| 4k | 159.3 | 24.2 | 18.2 GB | view |
| 8k | 146.5 | 24.1 | 19.2 GB | view |
| 16k | 148.9 | 21.6 | 20.7 GB | view |
| 32k | 142.2 | 18.7 | 23.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 25.9 | 1.00× |
| 2× | 27.1 | 1.05× |
| 4× | 31.5 | 1.22× |