← Back to community benchmarks

Qwen3.5-4B-OptiQ

M3 Max (40c) · 64 GB · 4bit · 2026-03-16
Performance
4k
tokens
1,279
PP tok/s
93.0
TG tok/s
3203
TTFT (ms)
4.1
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.2.13
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,028 98.3 4.0 GB view
4k 1,279 93.0 4.1 GB current
Batching Results
Batch Size TG tok/s Speedup
98.3 1.00×
177.8 1.81×
228.0 2.32×