← Back to community benchmarks
Qwen3.5-9B-mxfp4
Performance
4k
tokens
148.9
PP tok/s
20.6
TG tok/s
27512
TTFT (ms)
7.7
Peak mem (GB)
Hardware
Chip
M4 (8c)
Memory
16 GB
GPU Cores
8
Software
oMLX
v0.2.8
macOS
macOS 15.7.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 153.1 | 21.9 | 7.2 GB | view |
| 4k | 148.9 | 20.6 | 7.7 GB | current |
| 8k | 142.4 | 19.0 | 8.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 21.9 | 1.00× |
| 2× | 37.7 | 1.72× |
| 4× | 73.7 | 3.37× |