Qwen 3.8.

A reasoning-first branch that feels at home in a plan: it can turn an instruction into a sequence, a function call, or—in its larger form—a vision-aware answer.

View on Hugging Face See LocalEngine variants ↓

Model makerQwen

Supported in LocalEnginemacOS + iPhone & iPad

Upstream licenseApache-2.0

SourceQwen 3.8 model card ↗

Where it earns its space

Built for a real local rhythm.

These are good-fit starting points—not promises of benchmark performance. Choose the smallest listed option that comfortably covers your work.

Structured planning and task decomposition

Native function calling

Private reasoning on phone or Mac

In LocalEngine

Configured variants, by device.

The formats below are the downloads currently represented in LocalEngine’s model catalogs. GGUF runs through the llama.cpp-based runtime; MLX options use the Apple Silicon MLX runtime.

macOS

2B · 4B · 27B

Formats: GGUF Q4_K_M + BF16 projector on 27B · MLX 4-bit on 27B
Local note: 2B and 4B are text-only reasoning models; the 27B model adds image understanding.

iPhone & iPad

2B · 4B

Formats: GGUF Q4_K_M
Local note: Both mobile variants are text-only with native function calling; 4B suits newer hardware.

About the source

Model identity, task category, supported formats, and license are based on the linked Hugging Face Qwen 3.8 model card and the LocalEngine macOS/iOS catalogs. Hardware guidance reflects the packaged variants, not a universal system requirement.