deepseek-v4.1POST

DeepSeek V4.1 Flash 1017 on 4 DGX Sparks: 89.8 tok/s single user

Local deployment test with LibertAI 3.5bpw EXL3 quantization and no new kernels hits 89.8 tok/s for one user (vLLM: 48.5) and 202.9 tok/s with six.

Tech2Wild

@Tech2WildArchived 12 days agoOriginally posted 2026.10.18

Tech2Wild @Tech2WildOriginally posted 2026.10.18

Open original on X

🚀 DeepSeek V4.1 Flash 1017 now runs on TensorFold across 4 DGX Sparks ⚡️ 89.8 tok/s for 1 user (vLLM: 48.5) 🔥 202.9 tok/s with 6 users 🧠 LibertAI's 3.5bpw EXL3, every matrix 🛠️ No new kernels needed New default lane in the repo 👇 https://github.com/tonyd2wild/DeepSeek-V4.1-Flash-vLLM-DGX-Spark

x.com/tech2wild/status/2111658473138102300Archived 2026.10.18 16:25