Loading video...

Video Failed to Load

Go Home

DeepSeek-V4-Flash-Spark and Spark-Mini were born today. 1 command setup to Pi / vllm-studio / docker deployment. All this is running local on a single DGX Spark.

0xSero's profile picture

0xSero

52,357 subscribers

20,019 views • 2 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

This is a real task I gave to Qwen3.6-35B running on my DGX Spark, take 3 videos stitch them, and speed the first by 4x. This is something i have been using LLMs for over the last few months, Qwen was flawless! It contributed to local studio fixing the alignment issue u see
0:38

This is a real task I gave to Qwen3.6-35B running on my DGX Spark, take 3 videos stitch them, and speed the first by 4x. This is something i have been using LLMs for over the last few months, Qwen was flawless! It contributed to local studio fixing the alignment issue u see

0xSero

88,997 views • 1 month ago

It's been an amazing week for open models running on NVIDIA Local AI systems! 👀 Here's a few you’ll want to know about, all ready to run locally on NVIDIA RTX, DGX Spark, DGX Station, and Jetson.
1:30

It's been an amazing week for open models running on NVIDIA Local AI systems! 👀 Here's a few you’ll want to know about, all ready to run locally on NVIDIA RTX, DGX Spark, DGX Station, and Jetson.

NVIDIA RTX Spark

59,251 views • 7 days ago

I paired Cloudflare OS with self hosted deepseek-v4-flash and the result is freakin amazing Imagine running this setup inside DGX spark, you get fully private work companion solving all your work stuff The thing about this type of software is it already have a good harness and it probably can work out of the box with every open weight model Cant wait for the future
0:38

I paired Cloudflare OS with self hosted deepseek-v4-flash and the result is freakin amazing Imagine running this setup inside DGX spark, you get fully private work companion solving all your work stuff The thing about this type of software is it already have a good harness and it probably can work out of the box with every open weight model Cant wait for the future

Farhan Helmy

56,987 views • 15 days ago

Super cool to see Jensen NVIDIA showcasing Reachy Mini at his #CES26 keynote. Paired with a DGX Spark & Brev, it can make the perfect local home AI robotics setup!
0:20

Super cool to see Jensen NVIDIA showcasing Reachy Mini at his #CES26 keynote. Paired with a DGX Spark & Brev, it can make the perfect local home AI robotics setup!

clem 🤗

75,599 views • 7 months ago

Deepseek-V4-Flash helping me setup Nvidia's Dynamo for disaggregated inference. I have really gotten this model to be a daily driver now. It's really strong at agentic workflows and a decent programmer. For all my side stuff, it's local deepseek now Claude sub cancelled wdyt
0:41

Deepseek-V4-Flash helping me setup Nvidia's Dynamo for disaggregated inference. I have really gotten this model to be a daily driver now. It's really strong at agentic workflows and a decent programmer. For all my side stuff, it's local deepseek now Claude sub cancelled wdyt

0xSero

24,469 views • 3 months ago

Deekseek V4 Flash 0731 driving Kali Linux via Docker to reverse engineer Apples RDMA protocol to allow my Spark and MBP to talk to each other. Wild times.
0:29

Deekseek V4 Flash 0731 driving Kali Linux via Docker to reverse engineer Apples RDMA protocol to allow my Spark and MBP to talk to each other. Wild times.

Ash Hart

79,598 views • 6 days ago

Watch Gemma-4-26B running 18 concurrent sessions on a single NVIDIA AI DGX Spark — delivering a cumulative 300 tokens per second. 🔥
0:53

Watch Gemma-4-26B running 18 concurrent sessions on a single NVIDIA AI DGX Spark — delivering a cumulative 300 tokens per second. 🔥

Mia

22,995 views • 1 month ago

15 concurrent terminal workloads on a local DGX Spark, all served by nvidia/nemotron-3-super 120B A12B NVFP4 through vLLM. 15/15 completed, 0 errors, 30.2s wall time: no fake dashboard, just local inference under concurrent load. fineprint: live local concurrency demo
0:31

15 concurrent terminal workloads on a local DGX Spark, all served by nvidia/nemotron-3-super 120B A12B NVFP4 through vLLM. 15/15 completed, 0 errors, 30.2s wall time: no fake dashboard, just local inference under concurrent load. fineprint: live local concurrency demo

Joey

11,375 views • 2 months ago

This afternoon I picked up a new Nvidia DGX Spark computer with the goal of trying to run Gemma 4 31b (4bit) on it locally as a server. Just 1.5 hours later, it’s working! Using Open WebUI on my MacBook as the interface and it’s connecting to my DGX Spark running as a Gemma 4 server.
0:46

This afternoon I picked up a new Nvidia DGX Spark computer with the goal of trying to run Gemma 4 31b (4bit) on it locally as a server. Just 1.5 hours later, it’s working! Using Open WebUI on my MacBook as the interface and it’s connecting to my DGX Spark running as a Gemma 4 server.

Dave Lee

139,246 views • 4 months ago

image → 3D generation. a prompt is gently refined with Nemotron → FLUX paints a reference image → TRELLIS reconstructs a textured 3D mesh, running locally on an NVIDIA AI DGX Spark. quiet, local, always on.
0:43

image → 3D generation. a prompt is gently refined with Nemotron → FLUX paints a reference image → TRELLIS reconstructs a textured 3D mesh, running locally on an NVIDIA AI DGX Spark. quiet, local, always on.

three.ws

34,404 views • 1 month ago

This guy plugged a DGX Spark (the $3K Nvidia box) and a Mac Mini M4 together to run AI and what happened next surprised everyone > the Nvidia box handles the hard part - processing your prompt in milliseconds > Mac Mini M4 handles the fast part - generating the response at memory bandwidth speeds nothing else can match > together they hit 84 tokens per second on Llama - 6x faster than the Spark alone > running compute agents locally on this setup means your data never leaves your hardware > two boxes. two different architectures. one AI system that Deepseek runs at data center scale he ran it on his desk save this. the way we build local AI is about to change
18:41

This guy plugged a DGX Spark (the $3K Nvidia box) and a Mac Mini M4 together to run AI and what happened next surprised everyone > the Nvidia box handles the hard part - processing your prompt in milliseconds > Mac Mini M4 handles the fast part - generating the response at memory bandwidth speeds nothing else can match > together they hit 84 tokens per second on Llama - 6x faster than the Spark alone > running compute agents locally on this setup means your data never leaves your hardware > two boxes. two different architectures. one AI system that Deepseek runs at data center scale he ran it on his desk save this. the way we build local AI is about to change

Mr. Buzzoni

153,768 views • 2 months ago

I got NVIDIA’s PersonaPlex running on Reachy Mini and it’s uncanny. Ultra-low latency changes everything for voice agents. BTW, NVIDIA is offering a ~$7k prize (including a DGX Spark!) for the best Reachy Mini community app in the next 15 days.
0:39

I got NVIDIA’s PersonaPlex running on Reachy Mini and it’s uncanny. Ultra-low latency changes everything for voice agents. BTW, NVIDIA is offering a ~$7k prize (including a DGX Spark!) for the best Reachy Mini community app in the next 15 days.

Andi Marafioti

54,640 views • 6 months ago

From rockets to AI. Nine years after the original NVIDIA DGX-1 handoff, Jensen Huang delivered a brand-new DGX Spark to Elon Musk at Starbase. 🚀✨ The DGX Spark is a petaflop powerhouse built for creators, researchers, and developers — a desktop-sized supercomputer with five times the performance of the first DGX-1. Filmed at SpaceX’s rocket factory in Texas, this moment captures a conversation between the two visionariesI. ➡️ 📹 #SparkSomethingBig
1:12

From rockets to AI. Nine years after the original NVIDIA DGX-1 handoff, Jensen Huang delivered a brand-new DGX Spark to Elon Musk at Starbase. 🚀✨ The DGX Spark is a petaflop powerhouse built for creators, researchers, and developers — a desktop-sized supercomputer with five times the performance of the first DGX-1. Filmed at SpaceX’s rocket factory in Texas, this moment captures a conversation between the two visionariesI. ➡️ 📹 #SparkSomethingBig

NVIDIA

3,158,610 views • 10 months ago

I think I have made the coolest rig for an home AI setup. - 4× DGX Spark + OEM PSUs - 1× 8-port multi-gig switch - 8× short Cat6 - 1× vertical PDU / quality power strip - 3D printed chassis (and other small components + accessories) At the moment it is just a virtual replica. But if NVIDIA AI Developer wants to sponsor me with a real DGX Spark I am open to discuss
0:31

I think I have made the coolest rig for an home AI setup. - 4× DGX Spark + OEM PSUs - 1× 8-port multi-gig switch - 8× short Cat6 - 1× vertical PDU / quality power strip - 3D printed chassis (and other small components + accessories) At the moment it is just a virtual replica. But if NVIDIA AI Developer wants to sponsor me with a real DGX Spark I am open to discuss

Marco Franzon

44,346 views • 29 days ago

GLM-5.2 running under my desk, modifying GGUFs to enable MTP on the Spark. What a world we live in, where you can have a megamind running off electrons going really fast.
0:27

GLM-5.2 running under my desk, modifying GGUFs to enable MTP on the Spark. What a world we live in, where you can have a megamind running off electrons going really fast.

0xSero

23,422 views • 1 month ago

gemini 3.7 flash vs deepseek v4 pro 0813 vs muse spark 1.2 – on voxel city dioramas three models each built three crossy road-style 3d scenes – a construction site, a nyc intersection, a river with a drawbridge – as single self-contained html files the setup: Nous Research's hermes agent cli on OpenRouter, three.js skills preloaded, identical prompts per scene tasks: 1. construction site – tower crane on a working lift loop, paver laying fresh road, roller compacting it behind 2. nyc crossing – four-way intersection with a traffic light state machine, queuing cars, pedestrians crossing on the walk signal 3. river drawbridge – double-leaf bascule that lifts for tall boats, cars queuing at the barriers, animated water every scene: Three.js r185, box geometry only, a locked 20-color palette, four camera presets, and a day/night mode with bloom. one file, no build step, no assets models: Google DeepMind gemini 3.7 flash, DeepSeek v4 pro 0813, AI at Meta muse spark 1.2 muse and gemini finished every scene in two to three minutes. deepseek took 15 to 41 minutes per scene - build time, all three scenes #1 gemini 3.7 flash – 6m 43s #2 muse spark 1.2 – 7m 20s #3 deepseek v4 pro – 91m 25s - total tokens #1 muse spark 1.2 – 440,279 #2 gemini 3.7 flash – 713,855 #3 deepseek v4 pro – 20,957,568 - total price #1 muse spark 1.2 – $0.53 #2 gemini 3.7 flash – $0.56 #3 deepseek v4 pro – $4.57 - agent calls across the three builds #1 muse spark 1.2 – 12 #2 gemini 3.7 flash – 18 #3 deepseek v4 pro – 143 observations: • muse won two of the three scenes on looks with the smallest files in the test – 887 to 1,042 lines against gemini's 1,934 to 2,377. cheapest, fastest to a good frame, and shortest turned out to be the same column • deepseek burned 20.96m tokens – 29x gemini, 48x muse – across 143 agent calls. prompt caching is the only reason that cost $4.57: the cache discount absorbed roughly $30 of resent context • gemini was the only model whose files needed zero fixes to render – and the only one whose night mode is cosmetic. the sky never darkens and one camera button does nothing. clean code for a scene it never looked at follow thehype. for 24/7 ai news, analysis and breakdowns
0:45

gemini 3.7 flash vs deepseek v4 pro 0813 vs muse spark 1.2 – on voxel city dioramas three models each built three crossy road-style 3d scenes – a construction site, a nyc intersection, a river with a drawbridge – as single self-contained html files the setup: Nous Research's hermes agent cli on OpenRouter, three.js skills preloaded, identical prompts per scene tasks: 1. construction site – tower crane on a working lift loop, paver laying fresh road, roller compacting it behind 2. nyc crossing – four-way intersection with a traffic light state machine, queuing cars, pedestrians crossing on the walk signal 3. river drawbridge – double-leaf bascule that lifts for tall boats, cars queuing at the barriers, animated water every scene: Three.js r185, box geometry only, a locked 20-color palette, four camera presets, and a day/night mode with bloom. one file, no build step, no assets models: Google DeepMind gemini 3.7 flash, DeepSeek v4 pro 0813, AI at Meta muse spark 1.2 muse and gemini finished every scene in two to three minutes. deepseek took 15 to 41 minutes per scene - build time, all three scenes #1 gemini 3.7 flash – 6m 43s #2 muse spark 1.2 – 7m 20s #3 deepseek v4 pro – 91m 25s - total tokens #1 muse spark 1.2 – 440,279 #2 gemini 3.7 flash – 713,855 #3 deepseek v4 pro – 20,957,568 - total price #1 muse spark 1.2 – $0.53 #2 gemini 3.7 flash – $0.56 #3 deepseek v4 pro – $4.57 - agent calls across the three builds #1 muse spark 1.2 – 12 #2 gemini 3.7 flash – 18 #3 deepseek v4 pro – 143 observations: • muse won two of the three scenes on looks with the smallest files in the test – 887 to 1,042 lines against gemini's 1,934 to 2,377. cheapest, fastest to a good frame, and shortest turned out to be the same column • deepseek burned 20.96m tokens – 29x gemini, 48x muse – across 143 agent calls. prompt caching is the only reason that cost $4.57: the cache discount absorbed roughly $30 of resent context • gemini was the only model whose files needed zero fixes to render – and the only one whose night mode is cosmetic. the sky never darkens and one camera button does nothing. clean code for a scene it never looked at follow thehype. for 24/7 ai news, analysis and breakdowns

thehype.

27,710 views • 2 days ago

16 people chatting with Qwen3.6-35B at once ONE DGX Spark. This is a real capture, not a mockup: every token you see replays at its actual measured arrival time. Peaks ~440 tok/s total. A single user gets 105 tok/s. NVFP4 + MTP-3 on vLLM.
0:34

16 people chatting with Qwen3.6-35B at once ONE DGX Spark. This is a real capture, not a mockup: every token you see replays at its actual measured arrival time. Peaks ~440 tok/s total. A single user gets 105 tok/s. NVFP4 + MTP-3 on vLLM.

Wësche

26,094 views • 1 month ago

Introducing Spark 1 Pro and Spark 1 Mini 🔥 Two new models powering /agent, our state of the art agent that searches, navigates, and extracts web data from a prompt. Mini is 60% cheaper and Pro delivers higher accuracy, making this our most powerful extraction endpoint yet.
0:22

Introducing Spark 1 Pro and Spark 1 Mini 🔥 Two new models powering /agent, our state of the art agent that searches, navigates, and extracts web data from a prompt. Mini is 60% cheaper and Pro delivers higher accuracy, making this our most powerful extraction endpoint yet.

Firecrawl

30,284 views • 7 months ago

THE $4,000 DGX SPARK BENCHMARKS AT 342 T/S ON PROMPT PROCESSING - THEN DROPS TO 73 WHEN IT ACTUALLY GENERATES. that clip is a dgx spark running llama-bench on qwen3-coder 30b, side by side with a mac. two numbers decide everything here: pp512, prompt processing = 342 tokens/sec tg128, token generation = 73 tokens/sec that gap is the whole lesson. local ai isn't one speed, it's two. prompt processing is reading your input: your files, your long context. the spark is compute-heavy, so it eats that fast. token generation is writing the answer, and it's bound by memory bandwidth, where the spark is modest and unified-memory macs stay close. so "which box is faster" has no single winner. feeding huge context or running agents that read a lot? prompt processing wins, the spark shines. long chat replies, one token at a time? generation matters more, and a mac holds its own. no single benchmark number, no universal "fastest box", no upgrade that wins every workload. the uncomfortable part isn't that the spark is fast. it's that "tokens per second" was always two numbers, and the hype only ever quotes the flattering one. follow RetroChainer for the benchmark truth nobody screenshots, and bookmark this before you buy on one number.
1:14

THE $4,000 DGX SPARK BENCHMARKS AT 342 T/S ON PROMPT PROCESSING - THEN DROPS TO 73 WHEN IT ACTUALLY GENERATES. that clip is a dgx spark running llama-bench on qwen3-coder 30b, side by side with a mac. two numbers decide everything here: pp512, prompt processing = 342 tokens/sec tg128, token generation = 73 tokens/sec that gap is the whole lesson. local ai isn't one speed, it's two. prompt processing is reading your input: your files, your long context. the spark is compute-heavy, so it eats that fast. token generation is writing the answer, and it's bound by memory bandwidth, where the spark is modest and unified-memory macs stay close. so "which box is faster" has no single winner. feeding huge context or running agents that read a lot? prompt processing wins, the spark shines. long chat replies, one token at a time? generation matters more, and a mac holds its own. no single benchmark number, no universal "fastest box", no upgrade that wins every workload. the uncomfortable part isn't that the spark is fast. it's that "tokens per second" was always two numbers, and the hype only ever quotes the flattering one. follow RetroChainer for the benchmark truth nobody screenshots, and bookmark this before you buy on one number.

RetroChainer

42,451 views • 13 days ago