← Back to community benchmarks

Qwen3.5-4B

M2 (10c) · 8 GB · 4bit · 2026-03-11
Performance
4k
tokens
194.4
PP tok/s
25.0
TG tok/s
21066
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip M2 (10c)
Memory 8 GB
GPU Cores 10
Software
oMLX v0.2.7
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 201.6 32.0 3.9 GB view
4k 194.4 25.0 4.2 GB current
Batching Results
Batch Size TG tok/s Speedup
32.0 1.00×
44.5 1.39×