← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
568.8
PP tok/s
5.8
TG tok/s
1800
TTFT (ms)
22.8
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.2.6
macOS
macOS 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 568.8 | 5.8 | 22.8 GB | current |
| 4k | 675.4 | 5.7 | 23.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 5.8 | 1.00× |
| 2× | 9.9 | 1.71× |
| 4× | 19.2 | 3.31× |
| 8× | 35.9 | 6.19× |