Qwen 3.8 (27B, Q4)
Alibaba's Qwen 3.8 at 27B parameters: a dense, multimodal agentic model with native text, image, and video understanding, 262K context, flexible reasoning effort, MTP, and native tool calling. Q4_K_M is the practical on-device build for machines with 24GB+ usable memory.
| At a glance | |
|---|---|
| Made by | Alibaba |
| Download size | 16.5 GB |
| Parameters | 27B |
| Quantization | UD-Q4_K_M |
| Context window | 262K tokens |
| Uses tools | Yes |
| Best for | Everyday work |
| Runs on | llama.cpp, MLX |
| License | Apache 2.0 |
| Added to the catalog | 2026-10-04 |
Gezel downloads this model the first time a gezel needs it, checks the file against its published hash, and applies tuned settings for it.