Quick update on my latest experiment.
This is a AI post classified by Jev as Open & local models (a launch), kept by the AI Radar because it carries real work, not commentary.
Quick update on my latest experiment. After spending 1 day training Qwen3.5-4B with a 𝗰𝗼𝗴𝗻𝗶𝘁𝗶𝘃𝗲 𝗰𝗼𝗿𝗲, to think from first principles and use the tools at disposal to get an answer, I am testing the first prototype of what will become Javi1-4B! First impression, it's (kinda) working! Asked it for the latest @AnthropicAI model (opus 5.5) which clearly didn't have in it's dataset, and told it straight it didn't know and it would fetch it up! 🤩🤩🤩 Then got kinda stuck trying to get fetch it due to anti-bot mechanisms. Thanks @karpathy for the inspiration and @desamtralized for the model name s
Posted by Javier • priv/acc (4.4k followers) 1 h ago · 25 likes · 2.2k views · view the original post on X. Kept by the AI Radar as Open & local models.
More AI work like this
- Text to image just got a whole lot faster. Qwen Image 2.1 in GGUF format is here, ready… — @HuggingModels
- dear rtx 3060, 3070, 3080 and every 8gb to 12gb rtx owner, your gpu can run 27b dense… — @sudoingX
- Alright, the weird loop it got into fetching the information seems to be related to omp. — @jvr0x
- Meet Occamy 1.0 APEX I MiniPlus V2: a GGUF image-text-to-text model with 7.5k downloads.… — @HuggingModels
- this is what 12gb of vram builds in 2026, absolute magic — @sudoingX
- Run open models like Gemma 4 completely offline in the Antigravity SDK. — @antigravity
- Meet Occamy 1.0 APEX I MiniPlus V2.1 Abliterated GGUF. A custom quantized text… — @HuggingModels
- Getting access to quality healthcare often depends on where you live and whether a… — @NewsFromGoogle
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. 45.1k posts from 5k X accounts over the last 14 days, 1.9k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-23 20:32 UTC. Full method.