← Back to community benchmarks

Qwen3.5-4B

M1 (8c) · 16 GB · 4bit · 2026-03-09
Performance
1k
tokens
66.0
PP tok/s
13.1
TG tok/s
15525
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.6
macOS macOS 26.2
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 66.0 13.1 3.9 GB current
4k 63.1 12.2 4.2 GB view
Batching Results
Batch Size TG tok/s Speedup
13.1 1.00×
9.5 0.73×
12.8 0.98×
11.8 0.90×