DeepSeekHarnessにサブスクのCODEXを設定できた

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.

DeepSeekHarnessにサブスクのCODEXを設定できた Gpt-6 Lunaで遊べるドン！　237TPSだって

Posted by となりのトトノ🏯Local LLM | Tonoken3 (5.2k followers) 1 h ago · 5 likes · 381 views · view the original post on X. Kept by the AI Radar as Open & local models.

More AI work like this

• Meet altar-1: a text-generation model built on the GLM MoE architecture. With 739… — @HuggingModels
• New on the hub: MiMo-V2.6-Distill-Qwen-9B. A 9B image-text-to-text model built for… — @HuggingModels
• Paper thread on MiMo-V2.6, the newest open model and the latest to stream their RL run :) — @nrehiew_
• Ant Group’s Ling 3.0 Flash Fin is a finance-specialized open-weight model that delivers… — @ValsAI
• Koi pond local battle. Same 2 DGX Sparks each. Three Flash models. — @WescheNex1q
• Meet Qwen-72B: a massive 72B parameter text generation model. It handles both Chinese… — @HuggingModels
• A GLM-5.3 753B coding/cyber model that now fits on 2× Sparks — @0x0SojalSec
• I had Opus 5.5 build a tiny Sims town where every resident's dialogue is written live by… — @Tech2Wild

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. 43.6k posts from 5k X accounts over the last 14 days, 1.8k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-23 00:23 UTC. Full method.