← Back to community benchmarks

Qwen3.5-2B-OptiQ

M4 (10c) · 16 GB · 4bit · 2026-03-09
Performance
8k
tokens
857.7
PP tok/s
43.9
TG tok/s
9551
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 765.3 49.4 3.1 GB view
4k 865.8 46.6 3.3 GB view
8k 857.7 43.9 3.3 GB current
Batching Results
Batch Size TG tok/s Speedup
49.4 1.00×
93.3 1.89×
150.8 3.05×