← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
582.3
PP tok/s
5.5
TG tok/s
1759
TTFT (ms)
22.9
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.8
macOS
macOS 15.7.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 582.3 | 5.5 | 22.9 GB | current |
| 4k | 598.4 | 4.4 | 45.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 5.5 | 1.00× |
| 2× | 6.7 | 1.22× |