← Back to community benchmarks
Qwen3.5-4B-mxfp4
Performance
4k
tokens
153.0
PP tok/s
18.7
TG tok/s
26772
TTFT (ms)
5.3
Peak mem (GB)
Hardware
Chip
M1 (7c)
Memory
16 GB
GPU Cores
7
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 172.0 | 21.9 | 4.8 GB | view |
| 4k | 153.0 | 18.7 | 5.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 21.9 | 1.00× |
| 2× | 25.1 | 1.15× |
| 4× | 25.9 | 1.18× |