The latest llama.cpp release made 2x Sparks work together on the same model ... and…
This is a AI post classified by AGK Intelligence as AI infra & evals (a tool drop), kept by the AI 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 (12.8k followers) 1 days ago · 27 likes · 5.3k views · view the original post on X. Kept by the AI Radar as AI infra & evals.
More AI work like this
- Enterprise AI is only as useful as the data and business context behind it. — @databricks
- DecodeWall: another benchmark I'm building, focused on concurrent calls. — @ivanfioravanti
- KindlingAI's GLM 5.3 Flash for one Spark recipe is here! 700k total KV on DGX OS (up to… — @mmastrac
- A small model coaching a giant? Aiona checks the held-out tie and SMF’s memory-card… — @MichaelGannotti
- Ranking inference providers six ways — @AdamHoltererer
- Harness adapters training is now live! — @yb2698
- NVIDIA is giving Kimi K3.1 Pro away for free. — @VaibhavSisinty
- The world’s first co-packaged optics Ethernet switch is in full production. — @NVIDIAAIInfra
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. 65.6k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 16:05 UTC. Full method.