← Back to community benchmarks
qwen3.5-9b
Performance
1k
tokens
191.1
PP tok/s
20.9
TG tok/s
5358
TTFT (ms)
5.7
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 191.1 | 20.9 | 5.7 GB | current |
| 4k | 195.5 | 20.5 | 5.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 20.9 | 1.00× |
| 2× | 40.2 | 1.92× |
| 4× | 47.4 | 2.27× |