turboquant-wasm
AI
in-browser llm demo
SHOW HN2026
163points
62comments
#378of 4,366 in 2026
Top 9%of 2026 by points
How HN took it
MixedNo clear lean
7 positive, 11 neutral or asking, 0 mixed, 11 critical, out of 29 comments about the project. Thread score -0.16.
Performance: 2 for, 7 againstExecution: 3 for, 1 againstIdea: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Fast diagram generation and impressive output for a small local model
From 3 comments
just tried it out, must say it's amazing the speed at which it generates these diagrams Is this opensource by any chance? Would love to take a look at the code and understand how…
Sathwickp on HNvery interesting. Prompt to "generate System Design like ChatGPT end to end". Took about ~3-5 mins the model to download. It generated a reasonably good system design.
0xchamin on HNThat's amazing. Very good result. Thanks for sharing.
logicallee on HN
Gemma models are strong for their size
From 2 comments
The Gemma models really are amazing. I was on a flight a few days ago and used E2B to do some basic research on the place I was going to, running the model locally on my Pixel 10…
walthamstow on HNIt was genuinely outstanding for a tiny local model. I'm in Marrakech and it gave 3 separate one-day itineraries that contained most of the same stuff I got from Gemini when I…
walthamstow on HN
Objections
Downloads a 3.1GB model as soon as the page opens
From 3 comments
Yes. I tested it. It downloaded 3.1GB
avrionov on HNPlease never do this again. It's insane that the 3.1GB download kicks off as soon as you open the page.
Mystery-Machine on HNGiven what the page does, that's not a surprising amount, but consider it would take over 5 days to download on a 56k dialup connection, and even at 100Mbps that's over 4 minutes.
userbinator on HN
Shows unsupported browser/GPU error on some setups
From 1 comment
I love this idea. Unfortunately, it says "Unsupported browser/GPU" for me. This is Desktop Chrome version 147 (page says it requires 134+) and I have a 1060 card with 6 GB of RAM…
logicallee on HN
No Firefox support because WebGPU subgroups extension is missing
From 3 comments
firefox has webgpu already, but the subgroups extension isn't in yet. every matmul / softmax kernel here leans on subgroupShuffleXor for reductions, that's the blocker. same…
teamchong on HNno firefox support?
COOLmanYT on HNno firefox? sad :(
busssard on HN
Requests
Support for Firefox
From 2 comments
no firefox support?
COOLmanYT on HNno firefox? sad :(
busssard on HN
Shared model cache across sites or a model manager
From 2 comments
Ah let me clarify, many of the in the browser demos make me download certain models even if I already have them It would be great if there was a way that I don't have to…
hhthrowaway1230 on HNso multiple of these browser wasm demos make me re-download the models, can someone make a cdn for it or some sort u uberfast downloader? just throw some claude credits against…
hhthrowaway1230 on HN
Open source code
From 1 comment
just tried it out, must say it's amazing the speed at which it generates these diagrams Is this opensource by any chance? Would love to take a look at the code and understand how…
Sathwickp on HN
Questions
Is the 3.1GB download correct when visiting the page?
From 1 comment
Am I correct in interpreting the title to mean that visiting the page will result in a 3.1GB download?
userbinator on HN
How the compact code is turned into Excalidraw JSON
From 2 comments
How does this part work? "The LLM outputs compact code (~50 tokens) instead of raw Excalidraw JSON (~5,000 tokens)." I see on the left that the LLM is outputting some…
rahimnathwani on HNhad the same question! looks like it's another project called Drawmode[1] from the same group... [1] https://github.com/teamchong/drawmode
evrydayhustling on HN
Whether other models like Qwen were tried
From 1 comment
Very cool. Did you happen to try other models like Qwen and was there a difference as opposed to Gemma ?
agent37 on HN
Alternatives named
Mermaid diagrams generated by LLMs
From 2 comments
I've had excellent luck using Claude Code to generate "mermaid diagrams" for me, and convert them to .png format headlessly using mmdc/puppeteer. Really helped me out with an…
locusofself on HNdo the same. I just ask Claude code for mermaid to visualize any topic I'm discussing.
system_operator on HN
Skemio
From 1 comment
https://skemio.com
vismit2000 on HN
TikZ or SVG generation by LLM
From 2 comments
I now often have CC make technical/architecture diagrams with tikz, the results look much better than mermaid but still requires multiple iterations to fix bad arrows, bad…
d4rkp4ttern on HNI find Mermaid diagram rendering is quite ugly by default. I've gotten much better-looking results by asking it to just generate SVGs. As a bonus it can do animations too. e.g.…
ascorbic on HN