deepseek-v4.1-flash-vllm-dgx-spark
deepseek-v4.1-flash-vllm-dgx-spark is Run Deepseek V4.1 Flash 1017 on 2 x Sparks or 4 x Sparks on Tensorfold with SOLID speeds. It is ranked #600 on the Dev Radar, in Hosting & infra, first seen 54 days ago and shared in 19 posts (117.7k views).
What deepseek-v4.1-flash-vllm-dgx-spark says about itself
DeepSeek-V4.1-Flash-1017 on NVIDIA DGX Sparks with TensorFold + EXL3: TP4 (4 Sparks, 93.6 tok/s, 1M context) and TP2 (2 Sparks, 73 tok/s). Launchers, run records, measured numbers. Older vLLM lanes...
GitHub - tonyd2wild/DeepSeek-V4.1-Flash-TP2-and-TP4-DGX-Sparks: DeepSeek-V4.1-Flash-1017 on NVIDIA DGX Sparks with TensorFold + EXL3: TP4 (4 Sparks, 93.6 tok/s, 1M context) and TP2 (2 Sparks, 73 tok/s). Launchers, run records, measured numbers. Older vLLM lanes kept. · GitHub Skip to content Navigation Menu Sign in Search / Sign in Sign up Appearance settings You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} Repository navigation…
What people said about deepseek-v4.1-flash-vllm-dgx-spark on X
🚀 DeepSeek V4.1 Flash 1017 now runs on just 2x DGX Sparks 🔥 TensorFold's 2-node engine + LibertAI's EXL3 2.9 bpw pack: ⚡ 73 tok/s for 1 user, 136 tok/s total at 4 users 👤 84 tok/s per user solo 📥 93K-token prompt read in 43.7s (2,135 tok/s) 🧠 Full 1M context, loads in 27s 2 Sparks now beat our old 4-Spark vLLM…
— @Tech2Wild, 15 days ago · 170 likes · see the post
I ran my own benchmark on DeepSeek V4.1 Flash 1017 and here's what it scored on 4x DGX Spark 🔥 ⚡ 165.7 tok/s throughput 🎯 98.6 on my 69-scenario tool eval Full recipe 👇 https://github.com/tonyd2wild/DeepSeek-V4.1-Flash-vLLM-DGX-Spark
— @Tech2Wild, 17 days ago · 116 likes · see the post
🚀 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
— @Tech2Wild, 15 days ago · 87 likes · see the post
Alternatives to deepseek-v4.1-flash-vllm-dgx-spark
- boat — omfg @theo just released a video that talks about
- NVIDIA Technical Blog — Announced at GTC Berlin
- Alchemy — Run Kimi, GLM and DeepSeek models on Alchemy Inference. Low latency, high throughput and zero data retention. Sign up…
- Agent37 — Worth experimenting with if you're building agents
- Railway — Connect Neon
- vllm-ascend — What this PR does / why we need it? Add the Hy4 W8A8-MXFP8 deployment guide for Ascend 950DT, covering single-node,…
deepseek-v4.1-flash-vllm-dgx-spark in numbers
- Rank on the Dev Radar: #600 of 9203
- Shared in 19 posts by 6 accounts: @Tech2Wild, @ItsmeAjayKV, @ashxhart, @aijoey
- 117.7k views on those posts
- First seen 54 days ago, last shared 15 days ago
- Pricing seen by AGK Intelligence: open source
- Market: Hosting & infra
FAQ
What is deepseek-v4.1-flash-vllm-dgx-spark?
Run Deepseek V4.1 Flash 1017 on 2 x Sparks or 4 x Sparks on Tensorfold with SOLID speeds It was first shared on X 54 days ago and is ranked #600 on the Dev Radar.
Is deepseek-v4.1-flash-vllm-dgx-spark free?
It is open source.
Who shared deepseek-v4.1-flash-vllm-dgx-spark?
6 accounts on X, including @Tech2Wild, @ItsmeAjayKV, @ashxhart, in 19 posts totalling 117.7k views.
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. 31.3k posts from 5k X accounts over the last 21 days, 9.2k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-03 23:16 UTC. Full method.