← Back to community benchmarks
Qwen3.6-27B-oQ8-mtp
Performance
1k
tokens
202.8
PP tok/s
12.5
TG tok/s
5049
TTFT (ms)
28.3
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 202.8 | 12.5 | 28.3 GB | current |
| 4k | 189.9 | 12.1 | 29.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 12.5 | 1.00× |
| 2× | 24.2 | 1.94× |
| 4× | 23.8 | 1.90× |