← Back to community benchmarks
Qwen3.5-9B
Performance
8k
tokens
209.4
PP tok/s
19.0
TG tok/s
39126
TTFT (ms)
7.0
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.8
macOS
macOS 26.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 173.4 | 16.1 | 6.5 GB | view |
| 4k | 222.4 | 20.4 | 6.8 GB | view |
| 8k | 209.4 | 19.0 | 7.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 16.1 | 1.00× |
| 2× | 41.4 | 2.57× |
| 4× | 50.3 | 3.12× |