← Back to community benchmarks

Qwen3.5-4B

M1 (7c) · 16 GB · 4bit · 2026-04-06
Performance
4k
tokens
53.3
PP tok/s
11.5
TG tok/s
76905
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip M1 (7c)
Memory 16 GB
GPU Cores 7
Software
oMLX v0.3.4
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 45.1 8.7 3.3 GB view
4k 53.3 11.5 3.9 GB current
Batching Results
Batch Size TG tok/s Speedup
8.7 1.00×
14.3 1.64×
16.4 1.89×