← Back to community benchmarks
Qwen3.5-9B
Performance
16k
tokens
181.0
PP tok/s
7.4
TG tok/s
90530
TTFT (ms)
7.5
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 181.2 | 11.6 | 6.5 GB | view |
| 4k | 182.9 | 12.2 | 6.8 GB | view |
| 8k | 173.7 | 10.0 | 7.0 GB | view |
| 16k | 181.0 | 7.4 | 7.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 11.6 | 1.00× |
| 2× | 24.8 | 2.14× |
| 4× | 35.6 | 3.07× |