← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
16k
tokens
196.7
PP tok/s
26.2
TG tok/s
83312
TTFT (ms)
20.7
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
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 206.9 | 30.1 | 16.8 GB | view |
| 4k | 212.2 | 27.7 | 18.2 GB | view |
| 8k | 204.6 | 26.6 | 19.2 GB | view |
| 16k | 196.7 | 26.2 | 20.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 30.1 | 1.00× |
| 2× | 33.5 | 1.11× |
| 4× | 38.4 | 1.28× |
| 8× | 43.6 | 1.45× |