正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Testing app dev for Omarchy with Qwen3.8-Flash-Next running on one DGX Spark. It's so easy to get around.

Mia

48,099 subscribers

15,823 次观看 • 1 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

8 条评论

DHH 的头像

DHH1 天前

Going to make it even easier to use inference from any machine on your network on any other machine. So your M1 can use the Sparks without any hassle!

Mia 的头像

Mia1 天前

Beautiful can't wait For now I've just configured the models on Pi

Tyler Welton (spaceB0x) 的头像

Tyler Welton (spaceB0x)1 天前

Been using your implementation specifically on a single spark the last two weeks for app dev and security work. Been very impressed

Yule 的头像

Yule1 天前

Does dgx spark support omarchy without much hassle out the box

Andrey Kolesnikov 的头像

Andrey Kolesnikov1 天前

Should come like this from factory.

Synra 的头像

Synra1 天前

curious where the scan ran to blur a driver's license, something had to look at it first

Locust Plot 的头像

Locust Plot1 天前

I'm so torn between my m5u order and buying two sparks. Omarchy has been my daily driver.

Anders 的头像

Anders1 天前

I just installed "Try Omarchy" on my M5 Max. It runs crazy fast despite running virtual. Not sure I am ready to give up on the underlying OS yet.

相关视频

Qwen3.8 Flash on a single DGX Spark. Smooth experience!

Qwen3.8 Flash on a single DGX Spark. Smooth experience!

Mia

18,300 次观看 • 2 个月前

First impression of how fast the new Qwen3.8-Flash-Next runs on a single DGX Spark. 180B params, 262k context, all local.

First impression of how fast the new Qwen3.8-Flash-Next runs on a single DGX Spark. 180B params, 262k context, all local.

0xBakeer

22,118 次观看 • 2 个月前

Qwen3.8-next-flash has been going for 5 hours!!! on 3x DGX Spark. Prompt: make a photorealistic 3d version on San Francisco. It's got drone views, skateboarding, driving and junping around the map. GLM-5.3 and Flash were both done in an hour and put out garbage wtf

Qwen3.8-next-flash has been going for 5 hours!!! on 3x DGX Spark. Prompt: make a photorealistic 3d version on San Francisco. It's got drone views, skateboarding, driving and junping around the map. GLM-5.3 and Flash were both done in an hour and put out garbage wtf

0xSero

17,212 次观看 • 27 天前

Qwen3.8-27B is insane at browser use. Running on a DGX Spark, sped up 3x. The Qwen bros were right....!

Qwen3.8-27B is insane at browser use. Running on a DGX Spark, sped up 3x. The Qwen bros were right....!

0xSero

29,190 次观看 • 2 个月前

DeepSeek v4 Flash in one DGX Spark in action

DeepSeek v4 Flash in one DGX Spark in action

Mia

23,326 次观看 • 2 个月前

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.

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

20,019 次观看 • 5 个月前

I still can't believe I have this quality of AI on one DGX Spark. NVIDIA AI Qwen 3.8 Flash Next NVFP4, on vLLM

I still can't believe I have this quality of AI on one DGX Spark. NVIDIA AI Qwen 3.8 Flash Next NVFP4, on vLLM

Base Camp Bernie

16,314 次观看 • 1 个月前

Qwen3.8-Flash-Next (176B, NVFP4, 2× DGX Spark): 40,265 thinking tokens, 21,091 answer. Qwen3.8-27B on the same prompt: 42,988 thinking, 6,040 answer. Same question, same deliberation, 3.5× the output. 55 min vs 37 min. The 176B shipped a genuine leapfrog wave equation on a 512² lattice with reflections and interference. The 27B shipped a solid ripple tank. Both run 60fps in a single HTML file Generated on DGX Sparks on my desk.

Qwen3.8-Flash-Next (176B, NVFP4, 2× DGX Spark): 40,265 thinking tokens, 21,091 answer. Qwen3.8-27B on the same prompt: 42,988 thinking, 6,040 answer. Same question, same deliberation, 3.5× the output. 55 min vs 37 min. The 176B shipped a genuine leapfrog wave equation on a 512² lattice with reflections and interference. The 27B shipped a solid ripple tank. Both run 60fps in a single HTML file Generated on DGX Sparks on my desk.

Wësche

23,168 次观看 • 2 个月前

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.

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

60,853 次观看 • 2 个月前

Qwen3.8-Flash-Next Who's actually the winner on one DGX Spark? 🤔 My LLM Box (vLLM, NVFP4) vs TensorFold (MLX 4-bit) 🚀 c=1 -> difference: ~5 % ⚙️ c=16 -> difference: ~23 % 📊 Quality -> 6.5 vs 0 Total: 87 % vs 68 % 🏆 👉 More models coming soon 🥳

Qwen3.8-Flash-Next Who's actually the winner on one DGX Spark? 🤔 My LLM Box (vLLM, NVFP4) vs TensorFold (MLX 4-bit) 🚀 c=1 -> difference: ~5 % ⚙️ c=16 -> difference: ~23 % 📊 Quality -> 6.5 vs 0 Total: 87 % vs 68 % 🏆 👉 More models coming soon 🥳

vr8vr8

10,512 次观看 • 1 个月前

DeepSeek v4.1 Flash running on 2x DGX Sparks

DeepSeek v4.1 Flash running on 2x DGX Sparks

Mia

59,572 次观看 • 2 个月前

DeepSeek V4 Flash running on the DGX Station.

DeepSeek V4 Flash running on the DGX Station.

Matthew Berman

70,555 次观看 • 6 个月前

Running Qwen3.8-27B (the dense model, not Qwen Flash) on a single DGX Spark. Thanks to optimized caching algorithms and the StairCut method, the ~150k context prefill takes just milliseconds, and decoding speeds hit around 50–90 tok/s depending on the task. In this clip, I recorded after 5 hours of continuous running, I had Qwen design a pagoda garden and keep iterating and implementing new ideas nonstop.

Running Qwen3.8-27B (the dense model, not Qwen Flash) on a single DGX Spark. Thanks to optimized caching algorithms and the StairCut method, the ~150k context prefill takes just milliseconds, and decoding speeds hit around 50–90 tok/s depending on the task. In this clip, I recorded after 5 hours of continuous running, I had Qwen design a pagoda garden and keep iterating and implementing new ideas nonstop.

0xBakeer

29,359 次观看 • 1 个月前

Videos of Hermes Desktop using 2 x DGX Spark with: - GLM 5.3 Flash EXL3 - Qwen 3.8 Flash Next - DeepSeek V4 0731 Flash All powered by Mia recipes and her sparkDash!

Videos of Hermes Desktop using 2 x DGX Spark with: - GLM 5.3 Flash EXL3 - Qwen 3.8 Flash Next - DeepSeek V4 0731 Flash All powered by Mia recipes and her sparkDash!

Ivan Fioravanti ᯅ

45,257 次观看 • 2 个月前

GLM 5.3 Flash EXL3 running on 3x DGX Sparks.

GLM 5.3 Flash EXL3 running on 3x DGX Sparks.

Mia

12,535 次观看 • 1 个月前

Which DGX Spark is running Gemma 4?

Which DGX Spark is running Gemma 4?

Alex Ziskind

25,291 次观看 • 6 个月前

you're wasting hundreds on AI subscriptions I sat down with Ahmad Osman to learn how to run everything locally open-source models, DGX Spark vs Mac Studio, the new DeepSeek 4.1 Flash stop paying. start running.

you're wasting hundreds on AI subscriptions I sat down with Ahmad Osman to learn how to run everything locally open-source models, DGX Spark vs Mac Studio, the new DeepSeek 4.1 Flash stop paying. start running.

David Ondrej

17,691 次观看 • 21 天前

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.

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

55,032 次观看 • 9 个月前

Running GLM-4.7-Flash with OpenCode locally on M4 Max MacBook Pro. 4-bit model runs at 82 tok/sec. Prefill will get ~4x faster with M5 Max MacBook Pro (~28 Jan). EXO will also support disaggregating prefill and decode across devices, e.g. DGX Spark.

Running GLM-4.7-Flash with OpenCode locally on M4 Max MacBook Pro. 4-bit model runs at 82 tok/sec. Prefill will get ~4x faster with M5 Max MacBook Pro (~28 Jan). EXO will also support disaggregating prefill and decode across devices, e.g. DGX Spark.

Alex Cheema

128,404 次观看 • 9 个月前

Qwen3.8 Max UD-Q1_0 4× DGX Spark + llama.cpp/MTP3 53,448 tokens · 1h54m44s · 7.76 tok/s NVIDIA AI Qwen Qwen Developers

Qwen3.8 Max UD-Q1_0 4× DGX Spark + llama.cpp/MTP3 53,448 tokens · 1h54m44s · 7.76 tok/s NVIDIA AI Qwen Qwen Developers

Wësche

15,149 次观看 • 3 个月前