Hirundo says CCP-aligned censorship, propaganda or bias fell from 89.8% to 2.8% across 500 sensitive prompts after editing Qwen3.6-35B-A3B. Dramatic result, but still a company-run evaluation. #AI #Qwen…

#QP What The Friday is that? #WhatTheFriday

#ai8 #ai #aiart #aiartwork #aigenerated #aicommunity #aiartcommunity #aitraining #digitalart #creativeai #synthart #generativeart #Qwen #QwenImage21 #Qwen-Image-2.1 #Friday #WTF #AISLOP

One word prompt
“Fashionable”

#ai8 #ai #aiart #aiartwork #aigenerated #aicommunity #aiartcommunity #aitraining #digitalart #creativeai #synthart #generativeart #Fashionable #Qwen #QwenImage21 #Qwen-Image-2.1 #Fashion #Friday #FashionFriday

#QP Your one word prompt
“Fashionable”

#ai8 #ai #aiart #aiartwork #aigenerated #aicommunity #aiartcommunity #aitraining #digitalart #creativeai #synthart #generativeart #Fashionable #Qwen #QwenImage21 #Qwen-Image-2.1 #Fashion #Friday #FashionFriday

Working with text/code models is like molding clay. Working with image models is like shooting marbles and if you misplace a single word your marble goes shooting off across the driveway and gets stuck under the car. #AI #ComfyUI #Ollama #GooseAI #Qwen #Qwen-Image-2.1

水属性。（適当

#AIart
#AIイラスト
#digitalart
#Qwen-image-edit-2511
#Anima
#ComfyUI

One word prompt
“Inspiration”

#ai8 #ai #aiart #aiartwork #aigenerated #aicommunity #aiartcommunity #aitraining #digitalart #creativeai #synthart #generativeart #Inspiration #Qwen #QwenImage21 #Qwen-Image-2.1

One word prompt
“Inspiration”

#ai8 #ai #aiart #aiartwork #aigenerated #aicommunity #aiartcommunity #aitraining #digitalart #creativeai #synthart #generativeart #Inspiration #Qwen #QwenImage21 #Qwen-Image-2.1

#QP Your one word prompt
“Inspiration”

#ai8 #ai #aiart #aiartwork #aigenerated #aicommunity #aiartcommunity #aitraining #digitalart #creativeai #synthart #generativeart #Inspiration #Qwen #QwenImage21 #Qwen-Image-2.1

At its Apsara conference Alibaba said Qwen 4 is in training, teased models up to 10 trillion parameters, unveiled the Zhenwu V900 chip and targeted 20 gigawatts of cloud capacity by 2032.

#AI #Alibaba #Apsara #Chips #Cloud #Qwen #Yitian

⚙️ Local 27B on mining GPUs: faster inference with zero quality loss

Running Qwen3.8-27B on a dual CMP 50HX setup (Ivy Bridge platform) using MTP speculative decoding.

🔗 github.com/ggml-org/lla...

#localAI #llamaCpp #Qwen #CMP50HX #MTP

可愛いけど、もうちょっとバリエーションを増やしたいかな。

#AIart
#AIイラスト
#digitalart
#Qwen-image-edit-2511
#Anima
#ComfyUI

Discover how the Strata open-source AI engine allows users to run the 125-billion parameter Qwen3.8-Flash-Next model on 12GB consumer GPUs.

#StrataEngine #ArtificialIntelligence #Qwen #MachineLearning

うん、可愛い。

#AIart
#AIイラスト
#digitalart
#Qwen-image-edit-2511
#Anima
#ComfyUI

dnd.rostad.cc #svenska #sverige #dnd5e #aidungeon #qwen #stepfun #deepseek

Can a 125B model run on a 16GB GPU and still do real work?

I ran Qwen3.8-Flash-Next with Strata on an RTX 4060 Ti: ~60–70 tok/s, and it solved 2 of my 3 coding tasks. Catch: you need 64GB of RAM.

youtu.be/B77LasklmZU

#LocalAI #LocalLLM #Qwen

📝 「民主化するAI推論」——ゲーミングPCがデータセンターに変わる瞬間、Strataが示す推論格差の終焉

125億パラメーターのQwen3.8-Flash-NextをゲーミングPCで動かす「Strata」が登場。AI推論の民主化と、技術格差の縮小が現実になる理由を探る。

🔗 https://techscope365.com/3037/

#ロカルAI実行 #量子化 #Qwen #AI #テクノロジー

お嬢様感が強い

#AIart
#AIイラスト
#digitalart
#Qwen-image-edit-2511
#Anima
#ComfyUI

The DGX Spark 64GB launches October 23 from $4,999, with OEM-only builds, full model compatibility, and a price hike for the 128GB model.

#NVIDIA #DGXSpark #LocalAI #AIAgents #OpenSourceModels #ASUS #Qwen #EdgeAI

Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/s

#ai #artificialintelligence #qwen