look anon! someone with an rtx 3060 ti 8gb just opened a pr on my repo running bonsai 2…
This is a dev post classified by Jev as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
look anon! someone with an rtx 3060 ti 8gb just opened a pr on my repo running bonsai 2 27b at 32 → 43 tok/s. he built the kernel branch himself on windows, measured both binaries on the same card in the same session. the ladder so far, every row a different owner on their own card, same 5.9 GB file: > rtx 3060 ti 8gb: 32.44 → 43.40 tok/s, and the full 262k context fits in 7.7 GB > rtx 3060 12gb: 26 → 40 tok/s, 50 tok/s with the mtp head grafted back, greedy output bit identical > rtx 3090: 59.7 → 75.8 tok/s, measured by the prismml maintainers on their own box > rtx 4070 12gb: 51 → 103 tok
Posted by Sudo su (36.3k followers) 1 h ago · 24 likes · 1.6k views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: bonsai2-small-gpu.
More dev work like this
- UPDATE: Kev-0.6B, 4B, and 8B are now available. — @jaredpalmer
- Ok mcode looks nice and @u1tra_instinct made it better. Will try it as my CLI agent… — @MiaAI_lab
- AMD AI Developer Program is now open — @suraj_sharma14
- Ride the Pelican Express. Use Nautilo Designer right inside the desktop. — @Dan_Jeffries1
- Running an agent demo is easy. Operating one for a team is the hard part. — @DanKornas
- Boosting Matrix Multiplication Speed with NVIDIA cuBLAS! #BigData #Analytics… — @gp_pulipaka
- Backpropagation in Neural Networks. #BigData #Analytics #DataScience #AI… — @gp_pulipaka
- 🚀 New blog: Cosmos3 in RLinf: 3.33× End-to-End Evaluation Throughput with SGLang — @lmsysorg
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. 15.5k posts from 4.9k X accounts over the last 21 days, 1.7k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-20 16:47 UTC. Full method.