← Back to community benchmarks
Qwen3.5-27B-TurboQuant
Performance
1k
tokens
435.2
PP tok/s
18.5
TG tok/s
2353
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.4.4
macOS
macOS 26.5.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 435.2 | 18.5 | 15.8 GB | current |
| 4k | 473.8 | 18.1 | 17.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.5 | 1.00× |
| 2× | 32.6 | 1.76× |
| 4× | 43.6 | 2.36× |