Local LLM model page

Qwen 3.5 (0.8B)

The tiniest Qwen 3.5 — runs on any device including smartphones and Raspberry Pi. Hybrid thinking mode, 256K context, Apache 2.0. Perfect for on-device AI and embedded apps.

Find the best model for my hardwareBrowse all 183 LLMs
Parameters
0.8B
Minimum RAM
2 GB
Model size
0.6 GB
Quantization
Q4_K_M

Can Qwen 3.5 (0.8B) run locally?

Qwen 3.5 (0.8B) is best suited for entry-level laptops and desktops. LocalClaw recommends Q4_K_M as the default quantization, with at least 2 GB RAM.

Search term for LM Studio or compatible runtimes: qwen3.5-0.8b

Hugging Face repository: unsloth/Qwen3.5-0.8B-GGUF

chatcodeedgespeed

Strengths

  • The tiniest Qwen 3.5 — runs on any device including smartphones and Raspberry Pi. Hybrid thinking mode, 256K context, Apache 2.0. Perfect for on-device AI and embedded apps.

Limitations

  • Performance depends heavily on quantization, RAM bandwidth and runtime support.

Best use cases

  • chat
  • code
  • edge
  • speed

Benchmarks

Speed: 10/10

Quality: 4/10

Coding: 4/10

Reasoning: 3/10

Technical details

Developer: qwen

License: See model repository

Context window: Unknown tokens

Architecture: See model card

Released: 2026-03