← Back to community benchmarks

Qwen3.5-4B

M4 Pro (20c) · 48 GB · 4bit · 2026-03-10
Performance
1k
tokens
764.6
PP tok/s
82.9
TG tok/s
1339
TTFT (ms)
4.0
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 764.6 82.9 4.0 GB current
4k 792.8 77.5 4.2 GB view
Batching Results
Batch Size TG tok/s Speedup
82.9 1.00×
144.3 1.74×
178.4 2.15×