← Back to community benchmarks

Qwen3.5-4B

M1 (8c) · 16 GB · 4bit · 2026-03-12
Performance
4k
tokens
141.3
PP tok/s
20.3
TG tok/s
28995
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.9
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 145.3 21.5 3.9 GB view
4k 141.3 20.3 4.2 GB current
Batching Results
Batch Size TG tok/s Speedup
21.5 1.00×
19.9 0.93×
32.8 1.53×