GLM-5.3-Flash decodes code 1.2x faster than DeepSeek-V4.1-Flash-1017 on my Mac Studio M5…
This is a dev post classified by AGK Intelligence as AI dev tools (an opinion), kept by the Dev Radar because it carries real work, not commentary.
GLM-5.3-Flash decodes code 1.2x faster than DeepSeek-V4.1-Flash-1017 on my Mac Studio M5 Ultra 256 GB. DeepSeek gets to the first token sooner on long prompts. GLM-5.3-Flash: Decode, code: 84.9 tok/s Decode, prose: 87.3 tok/s First token, 16K prompt: 8.2 s First token, 32K prompt: 16.9 s First token, 64K prompt: 36.9 s First token, 128K prompt: 76.5 s 8 requests at once: 109.2 tok/s in total DeepSeek-V4.1-Flash-1017: Decode, code: 71.2 tok/s Decode, prose: 68.7 tok/s First token, 16K prompt: 7.7 s First token, 32K prompt: 15.2 s First token, 64K prompt: 31.5 s First token, 128K prompt: 66.0
Posted by Niklas (2.4k followers) 2 days ago · 39 likes · 5.3k 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
- Your AI remembered the wrong thing. Review it before it sticks. — @DanKornas
- Claude Sonnet 5.5 vs GPT-6.1 Terra for computer use. — @coastyai
- Hello everyone! — @KyleHessling1
- Your AI just got a sales team. — @theayush
- My most fun way of learning nowadays is asking AI to explain things to me. — @Chris_Wozniczek
- Claude Code tip: try medium effort before you pay for high; Karpathy built HackerTube on… — @russano
- My first day with Hermes — the full recap 😭 — @musecutething
- Meet DeepSeek-V4.1-Flash-1017-Uncensored-GSQ-RCO-IQ2_XXS-GGUF: a mouthful, but a beast!… — @HuggingModels
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. 31.4k posts from 5k X accounts over the last 21 days, 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 23:22 UTC. Full method.