Heard there's a 65B open model that beats Meta's 816B Muse Spark Open on Terminal-Bench…
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.
Ripple-65B Preview × DGX Heard there's a 65B open model that beats Meta's 816B Muse Spark Open on Terminal-Bench 2.1 (80.5 vs 76.4, self-reported), so I put it on the little NVIDIA GB10 box under my desk. Ripple-65B Preview from @RicursiveAI, dense, Apache 2.0. Then I pointed my Hermes Agent at it with a repo that had 4 failing tests. It read the code, found all 4 bugs, patched them and re-ran the tests. 5/5 pass in 1m 36s, 14 tool calls, about 44 W of GPU power. Setup: NVFP4 weights + DFlash2 speculative decoding, plus some tuning (fewer draft tokens, 3 concurrent requests, prefix cache)
Posted by HOPE. (2.5k followers) 1 days ago · 1 likes · 11 views · view the original post on X. Kept by the AI Radar as Open & local models.
More AI work like this
- Qwen 4 (unnamed quant) — @loktar00
- 北冥有鱼，其名为鲲。 — @NFT_Chen
- If you want to get started with Local AI but dunno where to start, THIS IS FOR YOU 🚨 — @javierbits
- 💥重磅！Qwen3.8-Flash-Next 量化版炸裂升级：Token消耗直接腰斩50%，准确率暴涨15%！本地32GB丝滑跑通125B级MoE！ — @NFT_Chen
- This could be so cool. — @niklaslenz_ai
- Qwen is teasing a new model — @RoundtableSpace
- 时代变了，以前是token每秒，有人提出了秒每token。。。。 — @mylifcc
- Qwen3.8-Flash-Next GGUFs now run faster with less thinking and less token use. — @UnslothAI
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. 65.6k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 16:05 UTC. Full method.