← Back to community benchmarks
Qwen3.6-27B-oQ4-fp16-mtp
Performance
1k
tokens
221.4
PP tok/s
33.3
TG tok/s
4626
TTFT (ms)
16.7
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
48 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 221.4 | 33.3 | 16.7 GB | current |
| 4k | 228.1 | 29.8 | 18.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 33.3 | 1.00× |
| 2× | 36.0 | 1.08× |
| 4× | 45.5 | 1.37× |