Qwen3.8-27B decodes code at 53.6 tok/s on one 16 GB RTX 5060 Ti and 154.5 tok/s on a…
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.
Qwen3.8-27B decodes code at 53.6 tok/s on one 16 GB RTX 5060 Ti and 154.5 tok/s on a 5090, with @MiaAI_lab's kit. RTX 5060 Ti 16 GB, EXL3 3.0 bpw: Decode, code: 53.6 tok/s Decode, prose: 52.1 tok/s Prefill, 32K prompt: 918 tok/s First token, 32K prompt: 35.7 s 500 words: about 13.5 s Two RTX 5060 Ti (32 GB in total), EXL3 4.0 bpw: Decode, code: 73.1 tok/s Decode, prose: 68.4 tok/s Prefill, 32K prompt: 996 tok/s First token, 32K prompt: 32.9 s 500 words: about 10.2 s RTX 5090 (32 GB), EXL3 4.0 bpw: Decode, code: 154.5 tok/s Decode, prose: 144.2 tok/s Prefill, 32K prompt: 3,116 tok/s First to
Posted by Niklas (2.4k followers) 59 min ago · 1 likes · 126 views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- DevX with NeoAstra is just phenomenal 🤩 using CodeAlta and GPT Luna 6 for a couple of… — @laurentkempe
- computer-repair-skill 这个开源项目很接地气，值得推荐。 — @bkdgiffug
- Your AI workflow doesn’t need five separate windows. — @DanKornas
- Claude Sonnet 5.5 vs GPT-6.1 Sol for computer use. — @coastyai
- TensorFold 1.2.0 decodes Qwen3.8-27B code at 268.6 tok/s on an RTX 5090, level with 1.1.2. — @niklaslenz_ai
- DeepSeek V4.1 Flash 1017 for 4x DGX Sparks got a lot of updates, with support for… — @MiaAI_lab
- Unsloth's 2-bit DeepSeek beat their own reference on a math test, by 2 answers out of 480. — @superalesha
- Vibe coding works when your agent has the right tools. — @apify
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. 31.3k posts from 5k X accounts over the last 21 days, 8.9k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-01 11:47 UTC. Full method.