← Back to community benchmarks

Qwen3.5-4B

M1 (8c) · 16 GB · 4bit · 2026-03-10
Performance
4k
tokens
136.6
PP tok/s
21.1
TG tok/s
29988
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.7
macOS macOS 15.7.4
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 141.9 21.0 3.9 GB view
4k 136.6 21.1 4.2 GB current
Batching Results
Batch Size TG tok/s Speedup
21.0 1.00×
33.1 1.58×
34.4 1.64×
29.1 1.39×