← Back to community benchmarks
Qwen3.5-27B
Performance
4k
tokens
121.4
PP tok/s
15.0
TG tok/s
33732
TTFT (ms)
17.0
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.6
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 126.8 | 15.3 | 16.6 GB | view |
| 4k | 121.4 | 15.0 | 17.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 15.3 | 1.00× |
| 2× | 29.6 | 1.93× |
| 4× | 32.7 | 2.14× |
| 8× | 33.5 | 2.19× |