← Back to community benchmarks
Qwen3.5-27B-6bit 22g
Performance
1k
tokens
56.9
PP tok/s
8.1
TG tok/s
18003
TTFT (ms)
22.9
Peak mem (GB)
Hardware
Chip
M2 Pro (19c)
Memory
32 GB
GPU Cores
19
Software
oMLX
v0.2.8
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 56.9 | 8.1 | 22.9 GB | current |
| 4k | 57.3 | 7.8 | 23.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 8.1 | 1.00× |
| 2× | 11.0 | 1.36× |
| 4× | 11.5 | 1.42× |