← Local AI Release Board

san-digital/Qwen3.8-Flash-Next-DFlash2

just landed · new, unvettedmodel

New, unvetted: created or first seen in the last few days, not from a trusted org and not past the signal threshold yet.

Text generation model from san-digital (HF pipeline tag; the card has no one-line description). Dense, 603M params. Context: 256K tokens (config). License: qwen-community-license-1.0-and-apache-2.0. Vendor-reported: "Warm-started from the 5-layer non-causal sliding-window DFlash2DraftModel (incoai/Qwen3.8-Flash-Next-DFlash2 revision a22a1744e85c17364dcc54a6a420af7135d4c7f6) with its rank-256 top-16 pairwise candidate selector."

Org
san-digital
Released
2026-11-15
Status
just landed · new, unvetted
License
qwen-community-license-1.0-and-apache-2.0 (restricted)
Parameters
603M
Architecture
dense · DFlash2DraftModel
Context
262,144 tokens (config.json)
Task
text-generation · text
Signal
2 HF likes · 51 downloads

Runs on

mixed: real files + estimate; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.

Links

First published here 2026-11-15 · updated 2026-11-16 · markdown · JSON