← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
194.4
PP tok/s
20.0
TG tok/s
5269
TTFT (ms)
6.5
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 194.4 | 20.0 | 6.5 GB | current |
| 4k | 176.5 | 13.5 | 6.8 GB | view |
| 8k | 124.5 | 9.3 | 7.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 20.0 | 1.00× |
| 2× | 19.5 | 0.97× |
| 4× | 26.5 | 1.32× |