← Back to community benchmarks

Qwen3.5-4B

M1 (8c) · 16 GB · 4bit · 2026-03-11
Performance
1k
tokens
123.0
PP tok/s
20.1
TG tok/s
8329
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.7
macOS macOS 15.6.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 123.0 20.1 3.9 GB current
4k 132.3 19.4 4.2 GB view
Batching Results
Batch Size TG tok/s Speedup
20.1 1.00×
30.5 1.52×
29.6 1.47×