The latest llama.cpp release made 2x Sparks work together on the same model ... and…
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.
The latest llama.cpp release made 2x Sparks work together on the same model ... and Qwen3.8-27B decoding got 81% faster. Normally pooing 2 DGX Sparks don't make a model twice as fast, but maybe that is changing? This is buried in the new llama.cpp v0.9.0 release. Multi-node tensor parallelism using NVIDIA NCCL is now supported. The developers tested Qwen3.8-27B Q4_K_M. One DGX Spark ⚡ Decode → 13.02 tps 📥 Prefill → 847 tps Two DGX Sparks: 🔥 Decode → 23.51 tps 🚀 Prefill → 1,348 tps That's ✅ 1.81× decode throughput ✅ 1.59× prefill throughput The model's computation is split across both
Posted by David Hendrickson (12.7k followers) 1 h ago · 2 likes · 288 views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- https://tasteskill.dev redesign is here! — @LexnLin
- Create a GIF of two guys playing basketball with a watermelon while a centaur does a… — @AdamHoltererer
- The GPT Image 2.6 API gives you more control over image complexity and lets you create… — @gabrielchua
- These 3D headphones come apart and reassemble. A WorkBuddy agent using Tencent's Hy4… — @kimmonismus
- ChatGPT Images 2.6 sets the scene. Tesseract brings it to life. — @trymirage
- is this gonna happen soon — @LexnLin
- Your coding agent can help script your TikToks. You still shoot the video. — @DanKornas
- 1 prompt and Images 2.6 made this — @vikktorrrre
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. 31.6k posts from 5k X accounts over the last 21 days, 9.3k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-05 01:03 UTC. Full method.