deepseek-v4.1POST

DeepSeek V4.1 Flash on 2× DGX Spark: 27s load, 2,059 tok/s on a 131K prompt

Using the TensorFold two-node engine and LibertAI's EXL3 2.9bpw pack, DeepSeek V4.1 Flash runs full 1M context on two DGX Sparks, loading in 27 seconds and reading a 131K-token prompt at 2,059 tok/s.

Tech2Wild

@Tech2WildArchived 12 days agoOriginally posted 2026.10.19

Tech2Wild @Tech2WildOriginally posted 2026.10.19

Open original on X

🚀 DeepSeek V4.1 Flash 1017 now runs on just 2x DGX Sparks 🔥 TensorFold 2-node engine + LibertAI's EXL3 2.9 bpw pack: full 1M context, loads in 27s, read a 131K-token prompt at 2,059 tok/s Speed numbers dropping soon 👀 Repo 👇 https://github.com/tonyd2wild/DeepSeek-V4.1-Flash-vLLM-DGX-Spark

x.com/tech2wild/status/2111977292427608497Archived 2026.10.19 12:01