perplexity-ai / pplx-computer-qwen-3-8-27b-dflash2-gguf-20260826
Other15.1K2Updated Aug 26, 2026
Downloads
15.1K
Likes
2
Last updated
Aug 26, 2026
License
Not available
llama.cpp GGUF build of the pplx-computer qwen3.8 27B checkpoint (Qwen35ForConditionalGeneration, dense hybrid GDN linear-attention + full attention every 4th of 64 layers), converted 2026-08-26 from the raw bf16 checkpoint. Ships two speculative-decoding drafts — pick one: th…
Tasks & library
- llama.cpp
Tags
- llama.cpp
- gguf
- speculative-decoding
- dflash2
- mtp
- conversational
Technical specifications
ParametersNot available
Libraryllama.cpp
LanguagesNot available
Base modelQwen/Qwen3.8-27B
LicenseNot available