WikiQwen 4B
🪴
Generate illustrated how‑to articles from any question
WikiQwen
Ask anything, get an illustrated how-to article: chat models, an illustration LoRA and the demo.
Note Try it: ask anything, get a step-by-step article with a picture for every step.
WikiQwen Plus
🪴Generate illustrated step‑by‑step how‑to articles
Note WikiQwen-4B writes, WikiQwen-Illustrator-9B draws: sharper pictures, same small GPU.
WikiQwen Pro
🪴Generate illustrated step-by-step how‑to articles from a question
Note WikiQwen-9B writes, WikiQwen-Illustrator-9B draws: the strongest pairing (best for logged-in users).
devon7y/WikiQwen-4B
Text Generation • 4B • Updated • 975 • 2Note Qwen3.5-4B fine-tuned to answer everything as an illustrated how-to article.
devon7y/WikiQwen-9B
Text Generation • 9B • Updated • 934Note Qwen3.5-9B fine-tuned the same way: more knowledgeable, a little slower than the 4B.
devon7y/WikiQwen-9B-FP8
Text Generation • 9B • Updated • 28Note Block-wise FP8 build of WikiQwen-9B: 11 GB, held-out loss +0.26%.
devon7y/WikiQwen-35B-A3B
Text Generation • 35B • Updated • 373 • 1Note The largest writer: Qwen3.6-35B-A3B mixture of experts, about 3B active per token.
devon7y/WikiQwen-35B-A3B-FP8
Text Generation • 35B • Updated • 8Note FP8 experts build of WikiQwen-35B-A3B: 37 GB, fits on one GPU.
devon7y/WikiQwen-Illustrator
Text-to-Image • Updated • 28 •Note Style LoRA for FLUX.2 [klein] base 4B that draws each step's caption.
devon7y/WikiQwen-Illustrator-9B
Text-to-Image • Updated • 8 •Note Style LoRA for FLUX.2 [klein] base 9B (FLUX Non-Commercial License): better hands and objects.