← Back to community benchmarks
Qwen3.5-9B
Performance
8k
tokens
220.3
PP tok/s
18.9
TG tok/s
37178
TTFT (ms)
7.0
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.2
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 223.9 | 21.1 | 6.5 GB | view |
| 8k | 220.3 | 18.9 | 7.0 GB | current |
| 16k | 201.9 | 16.6 | 7.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 21.1 | 1.00× |
| 2× | 40.9 | 1.94× |
| 4× | 48.6 | 2.30× |
| 8× | 49.1 | 2.33× |