← Back to community benchmarks
Qwen3.6-27B-oQ6-mtp
Performance
1k
tokens
201.8
PP tok/s
23.5
TG tok/s
5074
TTFT (ms)
23.0
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 | 201.8 | 23.5 | 23.0 GB | current |
| 4k | 162.8 | 20.5 | 24.4 GB | view |
| 8k | 156.7 | 14.8 | 25.4 GB | view |
| 16k | 111.6 | 2.5 | 26.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 23.5 | 1.00× |
| 2× | 6.0 | 0.26× |
| 4× | 12.1 | 0.51× |