← Back to community benchmarks
Qwen3.5-27B-TurboQuant
Performance
4k
tokens
38.6
PP tok/s
8.2
TG tok/s
106148
TTFT (ms)
10.9
Peak mem (GB)
Hardware
Chip
M4 (8c)
Memory
16 GB
GPU Cores
8
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 46.2 | 10.3 | 9.6 GB | view |
| 4k | 38.6 | 8.2 | 10.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 10.3 | 1.00× |
| 2× | 8.4 | 0.82× |
| 4× | 4.2 | 0.41× |