← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
120.3
PP tok/s
1.1
TG tok/s
8511
TTFT (ms)
22.4
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.9
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 120.3 | 1.1 | 22.4 GB | current |
| 4k | 136.5 | 1.1 | 22.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 1.1 | 1.00× |
| 2× | 2.3 | 2.09× |
| 4× | 4.5 | 4.09× |