← Back to community benchmarks
Qwen3.6-27B-oQ6-fp16-mtp
Performance
16k
tokens
83.2
PP tok/s
9.7
TG tok/s
196944
TTFT (ms)
26.7
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
64 GB
GPU Cores
24
Software
oMLX
v0.3.9
macOS
macOS 26.4
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 92.8 | 10.8 | 22.8 GB | view |
| 4k | 85.8 | 9.9 | 24.2 GB | view |
| 8k | 84.3 | 9.9 | 25.2 GB | view |
| 16k | 83.2 | 9.7 | 26.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 10.8 | 1.00× |
| 2× | 10.4 | 0.96× |
| 4× | 13.7 | 1.27× |
| 8× | 21.2 | 1.96× |