Qwen 27B Blend
Weights and memory
| Format | File size | Your device | Link | ||
|---|---|---|---|---|---|
| IQ3_S | 12.6 GB | 14.3 GB ◇ | Hugging Face | ||
| IQ4_XS | 14.3 GB | 15.8 GB ◇ | Hugging Face | ||
| 16.8 GB | 18.2 GB ◇ | Hugging Face | |||
| Q5_K_M | 19.5 GB | 20.7 GB ◇ | Hugging Face | ||
| 4-bit | 16.1 GB | 17.5 GB ◇ | Hugging Face | ||
| — | 55.6 GB | 54.3 GB ◇ | Hugging Face |
Published by the lab. File size is what the repository lists; for original weights it is the total of the weight files, which can include more than one variant. ● memory stated by the publisher · ◇ estimate from file size, an 8K-token context and 0.5 GB for the runtime. Unknown means there is no figure to go on. Checked 2026-10-11.
Tests on this site
Not in the first test roundCode, agent, embedding and safety models are listed with their sources only. What will be tested