← Back to community benchmarks

Qwen3.5-4B

M1 (8c) · 16 GB · 4bit · 2026-03-10
Performance
1k
tokens
145.6
PP tok/s
20.8
TG tok/s
7032
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.6
macOS macOS 26.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 145.6 20.8 3.9 GB current
4k 143.5 19.6 4.2 GB view
Batching Results
Batch Size TG tok/s Speedup
20.8 1.00×
33.0 1.59×
33.2 1.60×