← Back to community benchmarks
Qwen3.5-9B
Performance
64k
tokens
261.7
PP tok/s
24.8
TG tok/s
250416
TTFT (ms)
10.8
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
48 GB
GPU Cores
16
Software
oMLX
v0.2.6
macOS
macOS 26.2
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 363.5 | 49.0 | 6.7 GB | view |
| 4k | 364.0 | 48.6 | 7.0 GB | view |
| 64k | 261.7 | 24.8 | 10.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 49.0 | 1.00× |
| 2× | 72.2 | 1.47× |
| 4× | 75.4 | 1.54× |
| 8× | 75.7 | 1.54× |