← Back to community benchmarks
Qwen3.5-4B-mxfp4
Performance
4k
tokens
579.6
PP tok/s
64.4
TG tok/s
7067
TTFT (ms)
5.4
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
24 GB
GPU Cores
20
Software
oMLX
v0.2.11
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 674.6 | 70.9 | 5.0 GB | view |
| 4k | 579.6 | 64.4 | 5.4 GB | current |
| 8k | 557.6 | 54.0 | 6.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 70.9 | 1.00× |
| 2× | 112.1 | 1.58× |
| 4× | 142.4 | 2.01× |
| 8× | 136.8 | 1.93× |