← Back to community benchmarks
Qwen3.5-9B
Performance
4k
tokens
222.1
PP tok/s
18.1
TG tok/s
18443
TTFT (ms)
5.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 15.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 212.9 | 21.2 | 5.7 GB | view |
| 4k | 222.1 | 18.1 | 5.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 21.2 | 1.00× |
| 2× | 39.3 | 1.85× |
| 4× | 5.3 | 0.25× |
| 8× | 131.0 | 6.18× |