Hacker News: stfurkan

I'm currently working on an open-source LLM inference engine [1] for browsers via webGPU. If anyone wants to try or has any suggestions, I'm happy to listen :)

1. https://github.com/stfurkan/bitgpu

Demo: https://stfurkan.github.io/bitgpu/examples/chat.html

2. https://aidekin.com --> this is one of my project that's currently using bitgpu engine

New comment by stfurkan in "1-Bit LLM in the Browser"

stfurkan — Tue, 21 Jul 2026 06:58:58 +0000

Hi again :) I updated the engine and 27B model should work in the demo[1]. We can still consider it as experimental but I am trying to make it better and efficient.

1. https://stfurkan.github.io/bitgpu/examples/chat.html

New comment by stfurkan in "1-Bit LLM in the Browser"

stfurkan — Mon, 20 Jul 2026 17:20:02 +0000

Thank you :) I wanted to create it from zero myself so I can control it better. e.g. I started with ONNX support but now it support gguf models too. It might be a good idea to add some popular connectors in the future. Good luck with your project :)

New comment by stfurkan in "1-Bit LLM in the Browser"

stfurkan — Mon, 20 Jul 2026 12:34:48 +0000

Hello, I sent you a LinkedIn connection request. We can chat first and schedule a meeting. Thanks

New comment by stfurkan in "1-Bit LLM in the Browser"

stfurkan — Mon, 20 Jul 2026 12:33:22 +0000

Hi, the engine itself already has tool calling capabilities but if you're asking for the aidekin I didn't add tool calling there on purpose.

It needs webgpu support but I haven't had a chance to test with different devices.

New comment by stfurkan in "1-Bit LLM in the Browser"

stfurkan — Mon, 20 Jul 2026 08:48:53 +0000

Hi :) There are some smaller embedding and re-ranking models (I am currently using some of them on my aidekin project) but having it like bonsai models will be great to have.

New comment by stfurkan in "1-Bit LLM in the Browser"

stfurkan — Mon, 20 Jul 2026 08:44:36 +0000

Thank you for trying it :) I just added the 27B support 1 hour ago. Let me check and try to fix it. All other models should work as expected but if you have issues with them too, I can take a look.

New comment by stfurkan in "1-Bit LLM in the Browser"

stfurkan — Mon, 20 Jul 2026 08:16:46 +0000

I'm currently working on an open-source engine [1] exactly for this purpose. If anyone wants to try or has any suggestions, I'm happy to listen :)

1. https://github.com/stfurkan/bitgpu

2. https://aidekin.com --> this is one of my projects that's currently using bitgpu engine

New comment by stfurkan in "Speech Recognition and TTS in less than 500kb"

stfurkan — Sat, 18 Jul 2026 21:55:43 +0000

It looks great, thank you! I'll see if I can use it for my in browser AI assistant project's ( https://aidekin.com ) voice part. It's currently using Nemotron-3.5-ASR and supertonic-3 but overall it requires 1.2gb download.

New comment by stfurkan in "Ask HN: What Are You Working On? (July 2026)"

stfurkan — Mon, 13 Jul 2026 12:55:10 +0000

aidekin: an open-source, client-side AI assistant you drop onto any website. Your visitors get a private voice and text assistant that runs entirely on their own device via WebGPU

https://aidekin.com

https://github.com/stfurkan/aidekin

New comment by stfurkan in "Show HN: I wrote a 1-bit WebGPU runtime to run a 1.7B LLM in the browser"

stfurkan — Tue, 07 Jul 2026 19:08:02 +0000

Thank you :) Currently I am not planning to have hosted fallback Q&A but it's a nice idea. It should only download the ~300mb initially once and then use the cached model.

Show HN: I wrote a 1-bit WebGPU runtime to run a 1.7B LLM in the browser

stfurkan — Tue, 07 Jul 2026 17:05:21 +0000

Article URL: https://aidekin.com/

Comments URL: https://news.ycombinator.com/item?id=48820583

Points: 5

# Comments: 2

New comment by stfurkan in "Ask HN: What Are You Working On?"

stfurkan — Mon, 15 Jun 2026 17:51:33 +0000

I see, thanks for the feedback :) It'll be a nice addition to the game.

New comment by stfurkan in "Ask HN: What are you working on? (June 2026)"

stfurkan — Mon, 15 Jun 2026 17:50:12 +0000

Thank you for the feedback :) Letting players play before signing up might not be ideal for this case but I probably need to make the landing page better.

New comment by stfurkan in "Ask HN: What are you working on? (June 2026)"

stfurkan — Sun, 14 Jun 2026 17:51:44 +0000

https://duckville.town

You play a duck in a small shared town. You pick a job, pay rent, post on a Twitter-style feed, vote in local elections. The simulation keeps running when you close the tab. No PvP, no loot boxes, no combat. Playtime is a few minutes a day by design.

New comment by stfurkan in "Ask HN: What Are You Working On?"

stfurkan — Sat, 13 Jun 2026 13:51:52 +0000

Thank you :) There is a simple map currently but it can be improved. You can see it on this page after you sign in -> https://duckville.town/city

How can I make it better? I'd be happy to hear your feedback.

New comment by stfurkan in "Ask HN: What Are You Working On?"

stfurkan — Sat, 13 Jun 2026 11:18:15 +0000

https://duckville.town