Clover-35B-A3B decodes at 61.8 tok/s on a 16 GB RTX 5060 Ti, 2.4x faster than BF16 on…
This is a dev post classified by AGK Intelligence as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
Clover-35B-A3B decodes at 61.8 tok/s on a 16 GB RTX 5060 Ti, 2.4x faster than BF16 on one DGX Spark 16 GB, RTX 5060 Ti, Q4_0 Decode, code: 61.7 tok/s Decode, prose: 61.9 tok/s 500 words (code and prose): about 11.4 s Prefill at 8K: 992 tok/s First token at 32K: 39.9 s First token at 128K: 179.9 s Peak VRAM with the window 95% full: 14.8 GiB 1 DGX Spark, 128 GB, BF16, from my earlier post Decode, code: 25.7 tok/s Decode, prose: 26.0 tok/s 500 words (code and prose): about 27.0 s Prefill at 8K: 5771 tok/s First token at 32K: 6.6 s First token at 128K: 40.8 s 16 GB: Q4_0 GGUF (4.5 bpw, 18.2 Gi
Posted by Niklas (2.8k followers) 25 min ago · 0 likes · 70 views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: niklaslenz.com.
More dev work like this
- In the Code Arena: WebDev, Inkling 2 Small by @thinkymachines is #5 in Data & Analytics! — @arena
- A developer just squeezed this 284B-parameter DeepSeek model into 64GB of regular DDR5… — @TeksEdge
- Your AI trip plan shouldn’t need copying into another app. — @DanKornas
- A lot of people say OpenAI's computer use is better than Claude's, I don't think so… — @dwhitedesign
- This tiny chip lets an AI use your iPhone for you. — @VaibhavSisinty
- Why do we need WebMCP when a backend API already does the job? — @ChromiumDev
- 又变聪明了！Claude Code 云端 session 终于学会自己配环境了！ — @NFT_Chen
- Does anyone know if the Artificial Analysis decisions index is good? — @AdamHoltererer
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. 31.8k posts from 5k X accounts over the last 21 days, 9.5k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 21:57 UTC. Full method.