← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
223.7
PP tok/s
19.7
TG tok/s
4577
TTFT (ms)
6.5
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 223.7 | 19.7 | 6.5 GB | current |
| 4k | 225.2 | 20.3 | 6.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 19.7 | 1.00× |
| 2× | 40.2 | 2.04× |
| 4× | 52.8 | 2.68× |