← Back to community benchmarks
qwen3.5-9b
Performance
1k
tokens
569.0
PP tok/s
5.9
TG tok/s
1800
TTFT (ms)
22.8
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 569.0 | 5.9 | 22.8 GB | current |
| 4k | 721.6 | 5.7 | 23.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 5.9 | 1.00× |
| 2× | 5.4 | 0.92× |
| 4× | 7.2 | 1.22× |