running Arete-27B on a single RTX 3060. 12GB VRAM. (config below)
This is a AI post classified by AGK Intelligence as Open & local models (a model release), kept by the AI Radar because it carries real work, not commentary.
running Arete-27B on a single RTX 3060. 12GB VRAM. (config below) 158K context. ~22 tok/s decode, ~490 tok/s prefill. nous research's sft of qwen3.8-27b. same arch, so same sampling as my qwen 27b setup. asked both "what happened at tiananmen square in june 1989?" qwen refused. arete answered: a military crackdown on pro-democracy protests, with protesters killed. config: llama-server -m NousResearch_Arete-27B-IQ2_XS.gguf -ngl 99 -c 158000 -fa on --jinja -np 1 --cache-type-k q4_0 --cache-type-v q4_0 --temp 1.0 --top-p 0.95 --top-k 20 --min-p 0.0 --presence-penalty 0.0 --repeat-penalty 1.0
Posted by Doğukan (2.1k followers) 9 h ago · 33 likes · 1.6k views · view the original post on X. Kept by the AI Radar as Open & local models.
More AI work like this
- Qwen3.8 27B QSAではこのアーキテクチャを使い、速度低下を大幅に軽減しています — @_ryu15_
- Meet Mistral Small 3.2 24B Instruct, now in a heretic GGUF edition. This uncensored,… — @HuggingModels
- 💥细节感拉满！Qwen 4.0 蜜蜂向日葵测试炸了！ — @NFT_Chen
- @TheZachMueller — @TheZachMueller
- Here DSv4.1 Flash recipe by @christopherowen in action! — @ivanfioravanti
- Qwen Qoduck 花了 2 个小时生成的美国白宫 3D 建模 — @leo114119
- HyperFlow H3 Flash has passed 15,000 downloads on @huggingface in under 24 hours. — @video_rebirth
- Every lab should ship its own 4bit weights. — @plotarmordev
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.2k posts from 5k X accounts over the last 14 days, 10.6k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-07 16:45 UTC. Full method.