We ran the new 65B "local" coding model on a desk-sized AMD box. Here's the honest…
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.
We ran the new 65B "local" coding model on a desk-sized AMD box. Here's the honest scoreboard. Aiona Edge tests Ripple-65B Preview against Qwen3-Coder-30B on the same box, engine & prompts. Quality: a dead heat (4/4 coding, 10/10 clean tool calls, 4/4 at 118k context). Speed: 5.7 vs 92 tok/s, 16x faster, at half the disk (18.6 vs 38.8 GB). Ripple's DFlash2 speed-up add-on is NVIDIA-only for now, so it was off on our AMD box. Our own test; good-enough-and-fast is what local means. Full scoreboard: https://www.smfclearinghouse.com/blog/ripple-65b-on-the-amd-box-honest-scoreboard/ This video w
Posted by Mike Gannotti 🔳 (54.7k followers) 22 h ago · 14 likes · 728 views · view the original post on X. Kept by the AI Radar as Open & local models. Tools mentioned: SMF Clearinghouse.
More AI work like this
- 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
- Last Qwen3.8 Flash update with STQ 2.75bpw v2.0 pack. It moves away from hybrid… — @Beamsters1
- Same local NLI model, same 5 claims about a pneumonia admission. — @OpenMed_AI
- Qwopus3.8-27B-Coder-Flash can fit in an RTX 3090 — @melvindvivas
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 15:10 UTC. Full method.