Same Qwen3.8-Flash-Next. Same volcano prompt, word for word. Four days apart.
This is a AI post classified by Jev as Open & local models (a tool drop), kept by the AI Radar because it carries real work, not commentary.
Same Qwen3.8-Flash-Next. Same volcano prompt, word for word. Four days apart. One DGX Spark, Vic's EXL3 3.05bpw, thinking ON: 66K tokens in one shot, 17 min at 66 tok/s. Fewer bits. Fewer tokens. Half the time. Better island. What changed isn't the model: it's that we let it think. 131K characters of reasoning before the first line of HTML: atmosphere, lava paths, boat flee routes, a telemetry panel nobody asked for. Thinking off, this model writes what it sees. Thinking on, it designs. Disclosure: this is attempt 2 of 2: attempt 1 had a NaN in the lava curves. One TDZ fix on this one, ma
Posted by Wësche (2.9k followers) 22 h ago · 23 likes · 2.6k views · view the original post on X. Kept by the AI Radar as Open & local models.
More AI work like this
- dear rtx 3060 owners, and every 12gb card behind it. bonsai 2 27b dense went from 26 to… — @sudoingX
- Nimble is able to process images! — @madiator
- Woah...it claims to be open Jev. And it's 100% opensource. — @Saboo_Shubham_
- your rtx 3060 was running bonsai 2 at 26 tok/s this morning and now does 40 tok/s, i… — @sudoingX
- Meet DeepSeek-V4.1-Flash: a blazing fast image-text-to-text model. It takes both images… — @HuggingModels
- Meet Edge0-35B-A3B-preview: a 35B parameter MoE model built for edge inference. It runs… — @HuggingModels
- Putting Jeff-1 out into the world, this is an attempt at a Jev like model, built on qwen… — @DJLougen
- Train a 9M parameter language model from scratch in five minutes. — @tom_doerr
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 27.2k posts from 4.8k X accounts over the last 14 days, 1.2k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:50 UTC. Full method.