Qwen3.5 0.8B

About

The maker built it for trying out ideas, research, and further training on one narrow task.

How it compares

Of the chat models Outmake recommends for an 8 GB Mac, Outmake estimates it writes about 1.7 times as fast as Qwen3.5 2B, the next fastest.

Of the 7 chat models Outmake recommends for an 8 GB Mac, 5 read pictures and this is one. The two K2-Horizon models can't.

Of the 7 chat models Outmake recommends for an 8 GB Mac, it ranked 5th in Hugging Face downloads last month.

Limitations

Because it is small, the maker intends it for trials, research and further training.

Good to know

Its family practised by trial and reward in settings with a million agents, on tasks that grew harder.

Sources: Qwen/Qwen3.5-0.8B model card, Outmake's speed estimates, LM Arena and Hugging Face. Every line comes from one of these.

Run It Anywhere

Qwen3.5 0.8B is an open model, so any app that runs GGUF files can run it. These take the Q4_K_M size from unsloth straight from Hugging Face.

• LM StudioMac, Windows, LinuxOpen
• JanMac, Windows, LinuxOpen
• MstyMac, Windows, LinuxOpen
• OllamaMac, Windows, Linuxollama run hf.co/unsloth/Qwen3.5-0.8B-GGUF:Q4_K_MCopy
• llama.cppMac, Windows, Linuxllama-server -hf unsloth/Qwen3.5-0.8B-GGUF:Q4_K_MCopy
• Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/unsloth/Qwen3.5-0.8B-GGUF:Q4_K_MCopy