← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
211.7
PP tok/s
11.7
TG tok/s
4836
TTFT (ms)
9.8
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.5.dev1
macOS
macOS 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 211.7 | 11.7 | 9.8 GB | current |
| 4k | 217.7 | 11.3 | 10.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 11.7 | 1.00× |
| 2× | 23.1 | 1.97× |
| 4× | 37.7 | 3.22× |
| 8× | 38.9 | 3.32× |