asked for 2**200, base Qwen3.5-4B ran out of 4,096 tokens with no answer. Qwenputer…
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.
asked for 2**200, base Qwen3.5-4B ran out of 4,096 tokens with no answer. Qwenputer wrote all 61 digits, and the CPU that computed them is in its weights. four questions, one RTX 5090, greedy decoding: > base Qwen3.5-4B, no tool: no answer in 4,096 tokens on 3 of 4 > Qwenputer: 4 of 4 exact against Python > 29-digit x 29-digit multiply: 4.0 s on the Triton executor path > the quickstart on div's card ran as written
Posted by witcheer (22.8k followers) 1 days ago · 55 likes · 3.3k views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- 长PDF要是拆成单页再往一块拼，跨页表格和阅读顺序十有八九会乱套，这事你八成也烦过。 — @bkdgiffug
- Local models on Apple Silicon finally feel like a product, not a weekend project. — @PixelRainbowNFT
- GPT 6.1 Terra max vs GPT 6.1 Sol max — @HarshithLucky3
- Asked at the Meetup: "Does sbx run mistral work?" — @ajeetsraina
- Most agents freeze once deployed. — @GoogleCloudTech
- Your $250 GPU can now run a 35B coding model at 50 tokens/sec. — @0x0SojalSec
- Next week we're showing how to build self improving products. — @spenserskates
- Seedance 2.5 US Draft mode is now available on fal — @fal
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. 31.2k posts from 5k X accounts over the last 21 days, 8.8k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-10-30 22:12 UTC. Full method.