Views
No views yet
dnotitia/DNA3.0-27B, intended
for local inference with LM Studio and llama.cpp.Qwen/Qwen3.6-27B, with additional Korean, enterprise persona, and uncensored
post-training by Dnotitia. This repository does not add a separate
abliteration pass; it only converts and quantizes the published upstream
weights.| File | Purpose | Size |
|---|---|---|
DNA3.0-27B-Q4_K_M.gguf | Main language model, Q4_K_M | 16,547,399,264 bytes |
mmproj-DNA3.0-27B-Q8_0.gguf | Vision projector, Q8_0 | 629,247,424 bytes |
mmproj file and select it as the vision projector if your runtime does not
detect it automatically.kuper0201/DNA3.0-27B-GGUF.DNA3.0-27B-Q4_K_M.gguf.mmproj-DNA3.0-27B-Q8_0.gguf as well if you need image input.dnotitia/DNA3.0-27Bllama.cpp commit 6ea215d--no-mtp because the published model contains 64 main
transformer blocks plus separate MTP tensors.1745c63bdb76bada3f5b525eeab73bad9a53988e7eb98be865ba103e9ee41b084 DNA3.0-27B-Q4_K_M.gguf
228b0e39206f481da17c9ba1aa3d4d41f9df23d203bc51bb24f3f7e5c63e2cfe8 mmproj-DNA3.0-27B-Q8_0.gguf