I’ve moved my local LLM testing from manually coordinating/executing model tests in LM…
This is a AI post classified by AGK Intelligence as Open & local models (a tutorial), kept by the AI Radar because it carries real work, not commentary.
I’ve moved my local LLM testing from manually coordinating/executing model tests in LM Studio, to a Codex-managed llama.cpp workflow. It automates testing, pins model files and runtime settings, and captures results consistently for analysis. The setup targets my RTX 3080 10GB, using a consistent (51K) context window, and explicit reasoning-on and reasoning-off profiles. Tests cover speed, context handling, tool use and practical personal-agent tasks. Scores, timing, resource limits and incomplete responses all stay visible. I have a day job and a family, so the aim here is less orchestratio
Posted by GooGZ AI (1.6k followers) 11 h ago · 1 likes · 231 views · view the original post on X. Kept by the AI Radar as Open & local models.
More AI work like this
- 💥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
- Qwen 4 Unknown Preview bee on a sunflower. — @loktar00
- Meet DroidSenior-7B-v3-i1-GGUF: a 7B model fine-tuned for Android devs. Built on Qwen2… — @HuggingModels
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, 10.5k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-07 16:40 UTC. Full method.