GLM-5.3-Flash, a 321B MoE, decodes 16.0 tok/s on one DGX Spark with a 128K window
This is a dev post classified by AGK Intelligence as Other (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
GLM-5.3-Flash, a 321B MoE, decodes 16.0 tok/s on one DGX Spark with a 128K window 1 DGX Spark, 128 GB, Project Maya v1.1.53 Decode, code: 16.0 tok/s Decode, prose: 16.0 tok/s 500 words (code and prose): about 43.2 s Prefill at 8K: 689 tok/s First token at 32K: 46.9 s First token at 128K: 193.4 s Decode with a 128K prompt: 14.5 tok/s Quant: Maya-S IQ2_XXS, 96.5 GB, about 2.4 bpw All 12,096 experts fit in the Spark's memory pool Setup: the author's installer, 131,072 window as in the README's Spark row, 1 slot, MTP drafting Speed test: decode median of 2 runs, prefill of 3 or 4, 512 tokens, te
Posted by Niklas (2.8k followers) 1 h ago · 6 likes · 1k views · view the original post on X. Kept by the Dev Radar as Other. Tools mentioned: niklaslenz.com.
More dev work like this
- Human Computation! #BigData #Analytics #DataScience #AI #MachineLearning #IoT #IIoT… — @gp_pulipaka
- marin is the most exciting and ambitious open LLM training project. very excited to see… — @eliebakouch
- Most requested matchup yet: @MiaAI_lab's new GLM-5.3-Flash recipe on 2 DGX Sparks vs… — @niklaslenz_ai
- ChatGPT Images 2.6 is live in HeyGen. — @HeyGen
- Big news: Gemini Omni 1.2 Flash by @GoogleAI debuts at #1 in both Text-to-Video and… — @arena
- The GPT-Image 2.6 is a game changer for AI video generation, when combined with Minimax… — @cocktailpeanut
- feeling refreshed & ready to go — @elymadebynormal
- ICYMI: Here's what landed in October — @HeyGen
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, 9.4k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-05 23:17 UTC. Full method.