← Back to community benchmarks
Qwen3.5-9B
Performance
32k
tokens
107.6
PP tok/s
7.6
TG tok/s
304479
TTFT (ms)
8.5
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.2
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 185.8 | 19.9 | 6.5 GB | view |
| 4k | 165.7 | 16.8 | 6.8 GB | view |
| 8k | 109.4 | 12.3 | 7.0 GB | view |
| 16k | 100.3 | 14.7 | 7.5 GB | view |
| 32k | 107.6 | 7.6 | 8.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 19.9 | 1.00× |
| 2× | 19.5 | 0.98× |
| 4× | 20.4 | 1.03× |
| 8× | 26.7 | 1.34× |