← Back to community benchmarks
Qwen3.5-9B
Performance
16k
tokens
202.8
PP tok/s
17.8
TG tok/s
80787
TTFT (ms)
7.4
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.5
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 217.0 | 20.5 | 5.7 GB | view |
| 8k | 221.1 | 19.2 | 6.7 GB | view |
| 16k | 202.8 | 17.8 | 7.4 GB | current |
| 32k | 186.6 | 15.5 | 8.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 20.5 | 1.00× |
| 2× | 41.4 | 2.02× |
| 4× | 50.3 | 2.45× |
| 8× | 51.9 | 2.53× |