Qwen 3.5 (0.8B, Q4)
Alibaba's Qwen 3.5 at 0.8B parameters, the smallest of the family, with native tool calling and a 256K context window. Sized for phones and e-readers with 3-4 GB of memory.
| At a glance | |
|---|---|
| Made by | Alibaba |
| Download size | 0.5 GB |
| Parameters | 0.8B |
| Quantization | Q4_K_M |
| Context window | 256K tokens |
| Uses tools | Yes |
| Best for | Everyday work |
| Runs on | llama.cpp, MLX, Ollama |
| License | Apache-2.0 |
| Added to the catalog | 2026-09-27 |
Gezel downloads this model the first time a gezel needs it, checks the file against its published hash, and applies tuned settings for it.