← Back to community benchmarks
Qwen3.5-4B-mxfp8
Performance
4k
tokens
388.7
PP tok/s
21.1
TG tok/s
10539
TTFT (ms)
5.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 15.7
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 386.6 | 21.7 | 5.7 GB | view |
| 4k | 388.7 | 21.1 | 5.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 21.7 | 1.00× |
| 2× | 41.0 | 1.89× |
| 4× | 29.5 | 1.36× |