WebLLM
Shares rank 19 of 27 inference engines by recommenders
People recommend WebLLM as a free way to run language models fully in the browser on the GPU, offline once loaded. Critics say the project looks unmaintained.
People recommend WebLLM as a free way to run language models fully in the browser on the GPU, offline once loaded. Critics say the project looks unmaintained.
12 people gave an opinion
- recommend it
- 8
- criticize it
- 4
- approval share
- 67%
Recommended in 4 of 13 months
- November 2025: recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: not recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 8 people recommend itNeeds 10 or more, not met.
- 2 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 4 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Runs LLMs locally in the browser
“you would have a rather simple but capable LLM right in your browser using WebLLM and GPU”
Comment from 25 Mar 2026 in “Local LLM by Ente” “it's pretty decent and all in-browser/offline even for light tasks”
Comment from 4 Nov 2025 in “AI's Dial-Up Era” “definitely impressive that it runs in my browser”
Comment from 3 Sep 2026 in “WebLLM: high-performance in-browser LLM inference engine” - Comment from 6 Mar 2026 in “Show HN: PageAgent, A GUI agent that lives inside your web app”
Uses WebGPU for speed
“you would have a rather simple but capable LLM right in your browser using WebLLM and GPU”
Comment from 25 Mar 2026 in “Local LLM by Ente” “The WebGPU alternatives like WebLLM do not have the same access.”
Comment from 30 Apr 2026 in “Mozilla's Opposition to Chrome's Prompt API” “is more capable and will already work using WebGPU”
Comment from 30 Apr 2026 in “Mozilla's Opposition to Chrome's Prompt API”
What people warn about
Each mark is one comment
Appears unmaintained or outdated
“it hasn't been updated since Gemma 2”
Comment from 2 Sep 2026 in “WebLLM: high-performance in-browser LLM inference engine” “Project is de facto dead, used it for many years and had to rip it out 6 months ago”
Comment from 2 Sep 2026 in “WebLLM: high-performance in-browser LLM inference engine” “mostly abandoned since NVIDIA acquired OctoAI in late 2024”
Comment from 3 Sep 2026 in “WebLLM: high-performance in-browser LLM inference engine”
Other inference engines people recommend
The four most recommended other inference engines, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| vLLM | 112 | 56 | 67% | 12 | — | Approved |
| Strata | 31 | 15 | 67% | 5 | — | Approved |
| DwarfStar 4 | 26 | 2 | 93% | 6 | — | Approved |
| SGLang | 19 | 13 | 59% | 8 | — | — |
| WebLLMThis page | 8 | 4 | 67% | 4 | — | — |
What people said
12 of the 14 comments that mention it, newest first. Each links to the original comment.
“It works fine for me on Google Chrome on my MacBook Pro 14-inch M5 16GB RAM”
“definitely impressive that it runs in my browser”
“mostly abandoned since NVIDIA acquired OctoAI in late 2024”
“each browser session will result in a download of 500 MB to ~1 GB, depending on your model selection”
“it hasn't been updated since Gemma 2”
“Project is de facto dead, used it for many years and had to rip it out 6 months ago”
“The WebGPU alternatives like WebLLM do not have the same access.”
“is more capable and will already work using WebGPU”
“you would have a rather simple but capable LLM right in your browser using WebLLM and GPU”
“why not stay fully local with WebLLM”
“They are incredible for production, but they are "Blackboxes."”
“it's pretty decent and all in-browser/offline even for light tasks”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.