← Back to community benchmarks
Qwen3.6-27B-oQ4-fp16-mtp
Performance
1k
tokens
144.8
PP tok/s
18.8
TG tok/s
7072
TTFT (ms)
16.4
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.8
macOS
macOS 15.6.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 144.8 | 18.8 | 16.4 GB | current |
| 4k | 148.4 | 6.5 | 17.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.8 | 1.00× |
| 2× | 24.7 | 1.31× |
| 4× | 24.7 | 1.31× |