← Back to community benchmarks
Qwen3.5-27B-5bit
Performance
8k
tokens
96.7
PP tok/s
11.6
TG tok/s
84738
TTFT (ms)
20.6
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
64 GB
GPU Cores
16
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 99.5 | 12.5 | 19.8 GB | view |
| 4k | 100.1 | 12.1 | 20.1 GB | view |
| 8k | 96.7 | 11.6 | 20.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 12.5 | 1.00× |
| 2× | 15.5 | 1.24× |
| 4× | 16.0 | 1.28× |