← Back to community benchmarks

Qwen3.5-4B

M3 (10c) · 24 GB · 4bit · 2026-03-11
Performance
1k
tokens
337.8
PP tok/s
33.0
TG tok/s
3032
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip M3 (10c)
Memory 24 GB
GPU Cores 10
Software
oMLX v0.2.7
macOS macOS 15.7.4
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 337.8 33.0 3.9 GB current
4k 338.8 31.5 4.2 GB view
Batching Results
Batch Size TG tok/s Speedup
33.0 1.00×
63.3 1.92×
78.6 2.38×