← Back to community benchmarks

Qwen3.5-0.8B-OptiQ

M4 Pro (20c) · 64 GB · 4bit · 2026-03-15
Performance
1k
tokens
2,329
PP tok/s
257.5
TG tok/s
440
TTFT (ms)
1.8
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.2.12
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,329 257.5 1.8 GB current
4k 3,660 238.8 1.9 GB view
8k 3,809 216.7 1.9 GB view
Batching Results
Batch Size TG tok/s Speedup
257.5 1.00×
451.5 1.75×
619.3 2.41×