i spent two weeks living on every 100B+ model that fits one dgx spark 128gb and this is…
This is a vibe coding post classified by Jev as Agent infra & costs (a list of tools), kept by the Vibe Coding Radar because it carries real work, not commentary.
i spent two weeks living on every 100B+ model that fits one dgx spark 128gb and this is the list i wish existed the day the box landed. every option i could find, tested on this box, what survived is ranked below, all measured on my desk: > 1. qwen 3.8 flash next, 180B with 11B active, 44.4 tok/s, holds its speed at depth (-35% at 63K), 1M context fits in memory (measured to 128K) @Alibaba_Qwen official: http://huggingface.co/Qwen/Qwen3.8-Flash-Next > 2. ling 3.0 flash, 124B with 5.1B active, 42.1 tok/s on the official int4, mit license, the fastest vendor-official release on the board, op
Posted by Sudo su (36.2k followers) 7 days ago · 132 likes · 23.1k views · view the original post on X. Kept by the Vibe Coding Radar as Agent infra & costs.
More vibe coding work like this
- SpaceXAI is testing Remote Control in Grok Build. — @blankspeaker
- bonsai 2 27b just built this from one paragraph of prompt in one shot, all of it out of… — @sudoingX
- you can also use Jev to cut costs and token usage! — @tamarajtran
- Polsia now runs all company operations through a network of 9 agents, with a single… — @testingcatalog
- another terrible day for the “SaaS is dead” crowd — @tibo_maker
- Okay THIS is where agent infrastructure gets interesting. — @tonysimons_
- 3 settings inside my Hermes agent that turn it from "assistant" into "operator" 🚀🪽 — @BkashJosi
- 1 customer from $10k MRR 💸 — @tibo_maker
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 1.8k posts from 1.8k X accounts over the last 14 days, 141 tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 01:18 UTC. Full method.