FRAMEWIREIndonesiaUpdated Aug 26Live wire
0:00 / 0:00

Qwen3.8-Flash-Next from Alibaba_Qwen has day-0 support in Atomic Agent!

125B main model, 51B N-gram embeddings, 6B activated per token and 62.5 on SWE-bench Pro. We gave it a folder and it checked every file to sort them by content. Total: 25 steps + 230K tokens ≈ $0.07

Atomic AgentAug 2612
0:00 / 0:00

DeepSeek just turned V4 Flash into a vision-powered agent.

Not “upload an image and get a description.” It can see a screenshot, reason about what’s happening, use tools, and act on it.

Julian Goldie SEOAug 261
0:00 / 0:00

GLM-5.3-Flash vs. DeepSeek-v4-Flash

Same prompt, same harness (pi), same effort. GLM used 114k tokens over 93 turns taking 73min. Total cost 16 cents. DeepSeek used 70k tokens over 9 turns taking 10min. Total cost 2 cents. GLM is a richer scene but at 8x the cost and 7x the

Jackson AtkinsAug 2618
0:00 / 0:00

3.8 Flash Next runs perfectly on my Android phone (12GB RAM)

As you know, my Bigmoeonedge project enables running massive models on edge devices - such as a mid-range Android phone with 12GB of RAM. Following DeepSeek and various other models, Qwen 3.8 Flash Next

Raffaele ManciniAug 261