← Back to community benchmarks
Qwen3.5-9B
Performance
8k
tokens
210.4
PP tok/s
19.1
TG tok/s
38927
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 | 224.7 | 21.2 | 6.5 GB | view |
| 4k | 224.8 | 20.4 | 6.8 GB | view |
| 8k | 210.4 | 19.1 | 7.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 21.2 | 1.00× |
| 2× | 41.6 | 1.96× |
| 4× | 50.3 | 2.37× |