← Back to community benchmarks

Qwen3.5-2B-OptiQ

M4 (10c) · 16 GB · 4bit · 2026-03-09
Performance
8k
tokens
858.8
PP tok/s
44.0
TG tok/s
9539
TTFT (ms)
3.3
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.2.6
macOS macOS 26.3
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 767.6 49.5 3.1 GB view
4k 866.0 46.6 3.3 GB view
8k 858.8 44.0 3.3 GB current
32k 698.9 30.3 5.4 GB view
Batching Results
Batch Size TG tok/s Speedup
49.5 1.00×
94.4 1.91×
149.5 3.02×