← Back to community benchmarks

Qwen3.5-4B

M2 (10c) · 8 GB · 4bit · 2026-03-10
Performance
4k
tokens
198.0
PP tok/s
30.0
TG tok/s
20690
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip M2 (10c)
Memory 8 GB
GPU Cores 10
Software
oMLX v0.2.7
macOS macOS 15.7.4
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 199.1 31.8 3.9 GB view
4k 198.0 30.0 4.2 GB current
Batching Results
Batch Size TG tok/s Speedup
31.8 1.00×
44.0 1.38×
46.3 1.46×
39.0 1.23×