Qwen3.8-27B-Q4_K_M.gguf

---

license: apache-2.0 base_model: Qwen/Qwen3.8-27B pipeline_tag: text-generation tags:

• gguf
• qwen3.8

---

Qwen3.8-27B-GGUF (exact mirror, Q4_K_M)

Byte-for-byte mirror of the plain Q4_K_M GGUF and F16 vision projector originally published by Unsloth in unsloth/Qwen3.8-27B-GGUF (the plain Q4_K_M file has since been replaced upstream by Dynamic "UD" variants). Hosted here so the exact tested file stays at a stable address.

File	SHA-256	Bytes
Qwen3.8-27B-Q4_K_M.gguf	7e78da5d7e3ae28d178121f58646953305f3e5bd3cb46f4a75584e8b6c6fe169	17,106,775,008
mmproj-F16.gguf	cbb841a9ee0636b2ec172f5bb8df2ea8dfeb01e90fe7c6126581d662a0b4e43e	927,607,488

template and params pin the chat template and sampling parameters used with these files. Credit for the model and quantization belongs to Qwen and Unsloth; license Apache 2.0 as published.