After benching Qwen3.8 27B Kearuga via Aeon Bench, I came off with a disappointing score…
This is a AI post classified by Jev as Open & local models (a model release), kept by the AI Radar because it carries real work, not commentary.
After benching Qwen3.8 27B Kearuga via Aeon Bench, I came off with a disappointing score of 78.7... 🥲 Had to check the logs and found... > OpenClaw gave a harness error for everything > It was ran... with thinking 'off' 😂 Ah, so that's why the score is bad! xhigh eval again?
Posted by thewhitemage. (37.2k followers) 1 h ago · 1 likes · 77 views · view the original post on X. Kept by the AI Radar as Open & local models.
More AI work like this
- First test result using @Alibaba_Qwen Image 2.1 locally on @NVIDIAAI Dgx Spark.… — @SamJWasserman
- 3090 value just went up — @ItsmeAjayKV
- You can run locally Google's Nano Banano 2 level Image model Qwen-Image-2.1 on RTX 3090… — @0x0SojalSec
- Hahaha sooo cool.. have intermittent but continuous context compaction working.. that… — @u1tra_instinct
- proxmox frinkin rocks!! my personal agent and our family agent now have isolated mini… — @thekitze
- look anon! someone with an rtx 3060 ti 8gb just opened a pr on my repo running bonsai 2… — @sudoingX
- No Guardrails Qwen 2.1 Image — @Tech2Wild
- Qwen Image 2.1 is now open weight at just 7B parameters!! — @plotarmordev
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. 35k posts from 5k X accounts over the last 14 days, 1.5k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-20 21:11 UTC. Full method.