← Back to community benchmarks
Qwen3.5-9B
Performance
16k
tokens
341.1
PP tok/s
41.6
TG tok/s
48032
TTFT (ms)
7.6
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
24 GB
GPU Cores
16
Software
oMLX
v0.2.11
macOS
macOS 15.7.3
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 364.0 | 49.8 | 6.7 GB | view |
| 4k | 364.0 | 47.8 | 7.0 GB | view |
| 8k | 350.3 | 43.9 | 7.1 GB | view |
| 16k | 341.1 | 41.6 | 7.6 GB | current |
| 32k | 308.2 | 31.2 | 8.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 49.8 | 1.00× |
| 2× | 74.2 | 1.49× |
| 4× | 76.0 | 1.53× |