perplexity-ai / pplx-qwen-3-8-27b-dflash2-20260819
Other19B3244Updated Aug 24, 2026
Downloads
324
Likes
4
Last updated
Aug 24, 2026
License
other
Qwen3.8-27B (arch class Qwen35ForConditionalGeneration) quantized to NVFP4 (ModelOpt mixed-precision mirroring RadixArk/Qwen3.8-27B-NVFP4's recipe, FP8 KV cache) with one deliberate change: an unquantized bf16 lmhead (DFlash2 refuses a quantized one — every public NVFP4 quant …
Tags
- qwen3_5
- nvfp4
- modelopt
- speculative-decoding
- pplx-computer