← Back to community benchmarks

Qwen3.5-4B-mxfp4

M1 (7c) · 16 GB · 4bit · 2026-03-09
Performance
1k
tokens
172.0
PP tok/s
21.9
TG tok/s
5954
TTFT (ms)
4.8
Peak mem (GB)
Hardware
Chip M1 (7c)
Memory 16 GB
GPU Cores 7
Software
oMLX v0.2.6
macOS macOS 26.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 172.0 21.9 4.8 GB current
4k 153.0 18.7 5.3 GB view
Batching Results
Batch Size TG tok/s Speedup
21.9 1.00×
25.1 1.15×
25.9 1.18×