Mia's banner
Mia's profile picture

Mia

@MiaAI_lab • 29,418 subscribers

Building with AI & LLMs | Insights, recipes, tools & honest experiments

Shorts

Here's one way to get the most from Grok 4.5 ✨ Switching effort to "low" gives strong results on most tasks, near-zero quality loss, big usage savings — plus it's the fastest.

Here's one way to get the most from Grok 4.5 ✨ Switching effort to "low" gives strong results on most tasks, near-zero quality loss, big usage savings — plus it's the fastest.

1,312,268 views

People realizing they can run Opus-4.6 level intelligence on their laptop with Qwen3.8-27B. No subscription. No limits. Completely private.

People realizing they can run Opus-4.6 level intelligence on their laptop with Qwen3.8-27B. No subscription. No limits. Completely private.

167,311 views

DeepSeek v4.1 Flash on 3x DGX Sparks

DeepSeek v4.1 Flash on 3x DGX Sparks

30,649 views

One task, two models. GLM 5.3 Flash running slower at 25 tok/s prose Qwen3.8 Flash running faster at 47 tok/s prose Who will finish the task first?

One task, two models. GLM 5.3 Flash running slower at 25 tok/s prose Qwen3.8 Flash running faster at 47 tok/s prose Who will finish the task first?

27,249 views

Until there’s an official Grok Build app, you can still use it from your iPhone or Android with Termius (or any other SSH client). Just install Tailscale on your server, connect to the Tailscale IP in Termius, and run Grok Build from the command line as usual 👇

Until there’s an official Grok Build app, you can still use it from your iPhone or Android with Termius (or any other SSH client). Just install Tailscale on your server, connect to the Tailscale IP in Termius, and run Grok Build from the command line as usual 👇

15,627 views

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

DeepSeek v4.1 Flash via API is almost TOO fast 🤯
0:21
MiaAI_lab's profile picture

DeepSeek v4.1 Flash via API is almost TOO fast 🤯

Mia

137,788 views • 7 days ago

DeepSeek v4.1 Flash running on 2x DGX Sparks
0:35
MiaAI_lab's profile picture

DeepSeek v4.1 Flash running on 2x DGX Sparks

Mia

57,434 views • 3 days ago

Whoever made this is a genius 😂
1:45
MiaAI_lab's profile picture

Whoever made this is a genius 😂

Mia

244,982 views • 1 month ago

I ran this locally with GLM-5.3 Flash EXL3 on my DGX Sparks, and I think it beats both Fable 5.1 and GPT-6 Astra. The crazy part: it was faster to make create this on my sparks than it was with either Fable 5.1 or Astra. Live link here:
0:25
MiaAI_lab's profile picture

I ran this locally with GLM-5.3 Flash EXL3 on my DGX Sparks, and I think it beats both Fable 5.1 and GPT-6 Astra. The crazy part: it was faster to make create this on my sparks than it was with either Fable 5.1 or Astra. Live link here:

Mia

47,679 views • 7 days ago

Qwen3.8 Flash I really like this model and find it great for frontend. It performs much better than Qwen3.8 27B.
0:22
MiaAI_lab's profile picture

Qwen3.8 Flash I really like this model and find it great for frontend. It performs much better than Qwen3.8 27B.

Mia

61,327 views • 11 days ago

How DeepSeek v4.1 Flash looks on 3x DGX Sparks with 4 concurrent streams
0:50
MiaAI_lab's profile picture

How DeepSeek v4.1 Flash looks on 3x DGX Sparks with 4 concurrent streams

Mia

19,730 views • 4 days ago

I asked Claude Fable 5.1 to create the most beautiful single HTML file (incl. sound). I like it a lot. Full prompt + url below.
0:47
MiaAI_lab's profile picture

I asked Claude Fable 5.1 to create the most beautiful single HTML file (incl. sound). I like it a lot. Full prompt + url below.

Mia

30,125 views • 11 days ago

GLM 5.3 Flash on 2x DGX Sparks Look at the tok/s at the top :) This is prose. Releasing soon
0:23
MiaAI_lab's profile picture

GLM 5.3 Flash on 2x DGX Sparks Look at the tok/s at the top :) This is prose. Releasing soon

Mia

16,353 views • 7 days ago

DeepSeek V4 Flash Vision Exp is up & running on 2x DGX Sparks Native vision!!! 🔥🔥
0:23
MiaAI_lab's profile picture

DeepSeek V4 Flash Vision Exp is up & running on 2x DGX Sparks Native vision!!! 🔥🔥

Mia

29,326 views • 15 days ago

Here's Qwen3.8-Flash with the same prompt. It looks good, but it didn't do any firm grain, and misses many of the cool effects GLM 5.3 Flash added. Live demo:
0:29
MiaAI_lab's profile picture

Here's Qwen3.8-Flash with the same prompt. It looks good, but it didn't do any firm grain, and misses many of the cool effects GLM 5.3 Flash added. Live demo:

Mia

12,890 views • 6 days ago

Qwen3.8 Flash on a single DGX Spark. Smooth experience!
0:24
MiaAI_lab's profile picture

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

Mia

18,300 views • 11 days ago

I asked Ox Alpha to create the most beautiful and stunning single HTML file it could possibly imagine (sound on).
1:34
MiaAI_lab's profile picture

I asked Ox Alpha to create the most beautiful and stunning single HTML file it could possibly imagine (sound on).

Mia

26,008 views • 21 days ago

Addicted to Nous Research Hermes Agent's /learn. You can feed it any design and turn it into a reusable skill that makes Hermes design exactly how you want. /learn [URL or image] - extracts design tokens, layout structure, interaction states, component patterns, and a 10-point checklist Next time you want that exact style, just ask Hermes to use the skill it created. Example below 👇
0:29
MiaAI_lab's profile picture

Addicted to Nous Research Hermes Agent's /learn. You can feed it any design and turn it into a reusable skill that makes Hermes design exactly how you want. /learn [URL or image] - extracts design tokens, layout structure, interaction states, component patterns, and a 10-point checklist Next time you want that exact style, just ask Hermes to use the skill it created. Example below 👇

Mia

76,206 views • 2 months ago

you don't need an agent to git clone
0:21
MiaAI_lab's profile picture

you don't need an agent to git clone

Mia

20,197 views • 18 days ago

This is GLM-5.2 running on 3x DGX Sparks
0:54
MiaAI_lab's profile picture

This is GLM-5.2 running on 3x DGX Sparks

Mia

41,356 views • 1 month ago

Orinth-1.0-35b vs Qwen-3.6-27b I've asked both to build a single html file of Tetris game. First here's the Orinth 35b I think it did a fine job. Every control works, the game looks fine visually. How did Qwen 3.6 27b did? See post #2
0:40
MiaAI_lab's profile picture

Orinth-1.0-35b vs Qwen-3.6-27b I've asked both to build a single html file of Tetris game. First here's the Orinth 35b I think it did a fine job. Every control works, the game looks fine visually. How did Qwen 3.6 27b did? See post #2

Mia

62,696 views • 2 months ago

DeepSeek v4 Flash in one DGX Spark in action
0:30
MiaAI_lab's profile picture

DeepSeek v4 Flash in one DGX Spark in action

Mia

23,279 views • 26 days ago

Loading DeepSeek v4 Flash just reminded me how good and fast this model is and how well it runs on DGX Sparks. GLM-5.2 is really awesome, but if you want fast and concurrent inference, DS4F is still a top choice IMO. Created by DS4F in single shot The coffee guy
0:20
MiaAI_lab's profile picture

Loading DeepSeek v4 Flash just reminded me how good and fast this model is and how well it runs on DGX Sparks. GLM-5.2 is really awesome, but if you want fast and concurrent inference, DS4F is still a top choice IMO. Created by DS4F in single shot The coffee guy

Mia

39,686 views • 1 month ago

How prose looks like in Hermes agent using GLM 5.3 Flash EXL3 on 2x DGX Sparks
0:30
MiaAI_lab's profile picture

How prose looks like in Hermes agent using GLM 5.3 Flash EXL3 on 2x DGX Sparks

Mia

10,574 views • 16 days ago

Did you know Qwen 3.6 35B NVFP4 with 256k context, MTP, kv cache fp16 & image support takes around 68gb of VRAM? My NVIDIA AI DGX Spark can do 110 tok/s 👇
0:31
MiaAI_lab's profile picture

Did you know Qwen 3.6 35B NVFP4 with 256k context, MTP, kv cache fp16 & image support takes around 68gb of VRAM? My NVIDIA AI DGX Spark can do 110 tok/s 👇

Mia

35,255 views • 2 months ago