← Back to community benchmarks

Qwen3.5-4B

M1 (8c) · 16 GB · 4bit · 2026-03-10
Performance
4k
tokens
144.3
PP tok/s
20.8
TG tok/s
28394
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.7
macOS macOS 26.3
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 144.9 22.3 3.9 GB view
4k 144.3 20.8 4.2 GB current
Batching Results
Batch Size TG tok/s Speedup
22.3 1.00×
33.1 1.48×
34.1 1.53×
29.6 1.33×