Successfully Running the Mighty Mistral Small 4 119B on DGX Spark: A Feat of AI Efficiency

infrastructure#llm📝 Blog|Analyzed: Apr 28, 2026 04:46
Published: Apr 28, 2026 04:44
1 min read
Qiita LLM

Analysis

This is an incredibly exciting demonstration of pushing the boundaries of local AI hardware! Running a massive 119-billion Parameter model with 6.5B active parameters on the DGX Spark's 128 GiB unified memory showcases amazing Scalability. It is fantastic to see Open Source models like this making top-tier Inference accessible for cutting-edge experimentation.
Reference / Citation
View Original
"DGX Spark の 128 GiB ユニファイドメモリに UD-Q4_K_M (約 68.7 GiB, 3 シャード) がそのまま載ります。"
Q
Qiita LLMApr 28, 2026 04:44
* Cited for critical analysis under Article 32.