TensorFold 1.2.0 decodes Qwen3.8-27B code at 268.6 tok/s on an RTX 5090, level with 1.1.2.
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.
TensorFold 1.2.0 decodes Qwen3.8-27B code at 268.6 tok/s on an RTX 5090, level with 1.1.2. Prefill is 5.5 to 7.7% lower. RTX 5090 (32 GB), Qwen3.8-27B on TensorFold 1.2.0: Decode, code: 268.6 tok/s Decode, prose: 248.6 tok/s Prefill, 32K: 3,954 tok/s First token, 32K: 8.29 s 8 at once: 211.8 tok/s RTX 5090 (32 GB), Qwen3.8-27B on TensorFold 1.1.2 (Oct 24): Decode, code: 268.2 tok/s Decode, prose: 238.7 tok/s Prefill, 32K: 4,283 tok/s First token, 32K: 7.65 s 8 at once: 204.6 tok/s Single runs swing from 225.7 to 276.6 tok/s on code, so I took the median of three and read decode as level.
Posted by Niklas (2.4k followers) 1 h ago · 13 likes · 725 views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- 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
- DeepSeek V4.1 Flash 1017 for 4x DGX Sparks got a lot of updates, with support for… — @MiaAI_lab
- Vibe coding works when your agent has the right tools. — @apify
- 🔥必看！一个视频秒懂 DeepSeek Super-agent ！瞬间理解了梁圣的核心理念少占些注意力、多给些价值！ — @NFT_Chen
- Your coding agent says “done.” Where’s the evidence? — @DanKornas
- A $0.39 team of Qwen3.8 27B models just beat single call Fable 5 on a subset of… — @analogalok
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 10:52 UTC. Full method.