Mia's banner
Mia's profile picture

Mia

@MiaAI_lab • 25,653 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.

166,886 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

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

58,328 views • 3 days ago

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

Whoever made this is a genius 😂

Mia

244,502 views • 22 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

19,803 views • 3 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

17,880 views • 2 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

29,214 views • 7 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 • 13 days 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

19,905 views • 9 days 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

23,155 views • 18 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

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 • 8 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

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

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

62,672 views • 2 months 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

Ornith-1.0-9B for agentic coding? It broke on tool calling mid-task and got stuck in a loop with no way to continue. Only real upside: it's less bad than Gemma-4-12B... but that's not saying much. TL;DR: Skip it.
0:30
MiaAI_lab's profile picture

Ornith-1.0-9B for agentic coding? It broke on tool calling mid-task and got stuck in a loop with no way to continue. Only real upside: it's less bad than Gemma-4-12B... but that's not saying much. TL;DR: Skip it.

Mia

25,969 views • 2 months 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
MiaAI_lab's profile picture

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

Mia

23,132 views • 2 months ago

Nemotron-3-Nano-Omni-30B-A3B smashing 80 concurrent sessions on a single NVIDIA AI DGX Spark! 🔥 256k context. MTP enabled. All sessions running completely different prompts. ~800 tokens/s cumulative 🤯 Video starts slow but goes hard — watch till the end!
1:30
MiaAI_lab's profile picture

Nemotron-3-Nano-Omni-30B-A3B smashing 80 concurrent sessions on a single NVIDIA AI DGX Spark! 🔥 256k context. MTP enabled. All sessions running completely different prompts. ~800 tokens/s cumulative 🤯 Video starts slow but goes hard — watch till the end!

Mia

22,853 views • 2 months ago

Just did a quick test with Qwen 3.8 Preview — it seems to think for 10 minutes straight and still no results. Wasn’t even a hard prompt either… 🤷‍♀️
0:40
MiaAI_lab's profile picture

Just did a quick test with Qwen 3.8 Preview — it seems to think for 10 minutes straight and still no results. Wasn’t even a hard prompt either… 🤷‍♀️

Mia

17,616 views • 1 month ago

Qwopus 3.6-27b Coder I had a lot of requests to test it, so I did. I ran the same tests I’ve done on other models. It scored lower on tool-eval-bench than both Qwen 3.6 27b and Qwen 3.6 35b. It also produced broken single-file Tetris and Solar System HTML demos, even after 3 fresh attempts. In the Tetris html, the game stalled when you completed a line. It also randomly changed the pieces when moving them left or right. In the Solar System html, clicking on the sun or any planet broke the rendering — the objects just disappeared. Conclusion: The regular Qwen 3.6 27b and 35b models performed better. What do you think of Qwopus 3.6-27b Coder? Full results & RAW files: Full prompts in the posts below.
0:46
MiaAI_lab's profile picture

Qwopus 3.6-27b Coder I had a lot of requests to test it, so I did. I ran the same tests I’ve done on other models. It scored lower on tool-eval-bench than both Qwen 3.6 27b and Qwen 3.6 35b. It also produced broken single-file Tetris and Solar System HTML demos, even after 3 fresh attempts. In the Tetris html, the game stalled when you completed a line. It also randomly changed the pieces when moving them left or right. In the Solar System html, clicking on the sun or any planet broke the rendering — the objects just disappeared. Conclusion: The regular Qwen 3.6 27b and 35b models performed better. What do you think of Qwopus 3.6-27b Coder? Full results & RAW files: Full prompts in the posts below.

Mia

11,183 views • 2 months ago

No more content to load