← Back to community benchmarks

Qwen3.5-2B

M4 (10c) · 16 GB · 4bit · 2026-03-09
Performance
1k
tokens
1,043
PP tok/s
83.9
TG tok/s
982
TTFT (ms)
2.5
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.2.6
macOS macOS 26.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,043 83.9 2.5 GB current
4k 1,038 80.5 2.5 GB view
8k 1,020 76.0 2.6 GB view
Batching Results
Batch Size TG tok/s Speedup
83.9 1.00×
157.9 1.88×
204.5 2.44×