← Back to community benchmarks
Qwen3.5-9B
Performance
4k
tokens
677.0
PP tok/s
5.5
TG tok/s
6051
TTFT (ms)
23.0
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.2.7
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 560.8 | 5.6 | 22.8 GB | view |
| 4k | 677.0 | 5.5 | 23.0 GB | current |
| 8k | 612.1 | 5.4 | 23.2 GB | view |
| 16k | 590.9 | 5.2 | 23.7 GB | view |
| 32k | 460.1 | 4.2 | 24.7 GB | view |
| 64k | 335.9 | 3.6 | 27.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 5.6 | 1.00× |
| 2× | 7.5 | 1.34× |
| 4× | 15.3 | 2.73× |
| 8× | 30.6 | 5.46× |