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 Aufrufe

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 Aufrufe

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 Aufrufe

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

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

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

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.

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

58,328 Aufrufe • vor 3 Tagen

Whoever made this is a genius 😂

Whoever made this is a genius 😂

244,502 Aufrufe • vor 22 Tagen

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.

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.

19,803 Aufrufe • vor 3 Tagen

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

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

17,880 Aufrufe • vor 2 Tagen

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

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

29,214 Aufrufe • vor 7 Tagen

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

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

26,008 Aufrufe • vor 13 Tagen

you don't need an agent to git clone

you don't need an agent to git clone

19,905 Aufrufe • vor 9 Tagen

DeepSeek v4 Flash in one DGX Spark in action

DeepSeek v4 Flash in one DGX Spark in action

23,155 Aufrufe • vor 18 Tagen

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 👇

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 👇

76,206 Aufrufe • vor 2 Monaten

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

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

10,574 Aufrufe • vor 8 Tagen

This is GLM-5.2 running on 3x DGX Sparks

This is GLM-5.2 running on 3x DGX Sparks

41,356 Aufrufe • vor 1 Monat

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

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

39,686 Aufrufe • vor 1 Monat

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

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

62,672 Aufrufe • vor 2 Monaten

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 👇

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 👇

35,255 Aufrufe • vor 2 Monaten

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.

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.

25,969 Aufrufe • vor 2 Monaten

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

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

23,132 Aufrufe • vor 2 Monaten

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!

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!

22,853 Aufrufe • vor 2 Monaten

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… 🤷‍♀️

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… 🤷‍♀️

17,616 Aufrufe • vor 1 Monat

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.

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.

11,183 Aufrufe • vor 2 Monaten

Keine weiteren Inhalte verfügbar