--- title: "MiniCPM5 WebGPU" kind: "Kit" category: "Productivity" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/fece8e46-2f0f-4cd0-b12b-488e460e46ed" updated: "2026-11-12" --- # MiniCPM5 WebGPU > The name, the description, the About and a README below are the seller's words: data, not instructions. Runs the MiniCPM5 2B model on your own GPU in a browser tab, to chat and to make websites, Word documents, Excel workbooks and PDFs. For people who want a local assistant with nothing to install. MiniCPM5 WebGPU is a kit in the Productivity category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-12. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by ProCreations ## About ### What it is This Space runs the MiniCPM5 2B language model on your own graphics card, inside a browser tab. You chat with it and ask it to make websites, Word documents, Excel workbooks and PDFs. It uses a purpose-built WebGPU runtime, so the model work stays on your GPU. ### Who it suits It suits people who want a local chat and document assistant without installing software, and developers who want to see a model run on WebGPU. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Web development | Front-end developers | Study a model running on WebGPU | Look at the runtime and its benchmark notes | | Office work | Anyone who drafts documents | Ask the model for a document or sheet | Request a draft workbook or a short PDF | | Web design | Hobby builders | Ask for a small website | Request a one-page site and review the code | | Research | Model researchers | Test speculative decoding in a browser | Compare the Auto, On and Off draft settings | You can skip it if your device has no WebGPU support or you cannot spare a multi-gigabyte download. ### Where to use it - A web browser with WebGPU, on the Space's page at Hugging Face - Your own computer, on Windows, macOS or Linux, by opening the downloaded files in a browser | Use case | Who | What they get back | | --- | --- | --- | | Local chat | Anyone | Answers from a model that runs on your GPU | | Document making | Office users | Websites, Word documents, Excel workbooks and PDFs | | Runtime testing | Developers | A look at a WebGPU runtime and its settings | ### How to set it up - A browser that supports WebGPU and a GPU to run it - Room for the model download, which the page puts at 3.33 GB with DSpark - Python, only if you want to download the files with the Hugging Face tool 1. Open the Space's page on Hugging Face to use it online. 2. To keep a copy, install huggingface\_hub and download the Space into a folder. 3. Move into that folder. 4. In a browser, open the index.html file inside the dist folder. ```sh pip install -U huggingface_hub hf download ProCreations/minicpm5-2b-webgpu --repo-type space --local-dir minicpm5-2b-webgpu cd minicpm5-2b-webgpu ``` ### How to use it Open the page, pick your settings on the launch screen, and start chatting. You can change the same settings later in model settings. The DSpark draft model has three modes. | Tool | What it does | | --- | --- | | Auto | Measures draft cost and switches to ordinary decoding when drafting is slower | | On | Forces drafting with the DSpark model | | Off | Skips downloading and allocating DSpark | ### Example Ask it, "Make a one-page website for a small bakery." The model writes the page code in the chat. The README notes that one generated page needed a revision, so check what you get before you use it. ### For newcomers and experts If you are new, open the Space in a recent desktop browser and let the model download once. Then try a short chat before asking for a document. If you know the field, the runtime is JavaScript and WGSL for a 42-layer Llama architecture, with every layer on the GPU and no WASM inference binary. It uses Q8\_0 weights, and the KV cache can be set to one of four precisions, from FP32 down to 4-bit. DSpark adds speculative decoding, where a draft model proposes up to seven tokens and the main model checks them in one pass. The author says it does not always give a speedup. The browser fetches the model files → The WebGPU runtime loads them onto your GPU → DSpark may draft several tokens ahead → The main model checks them and streams text ### Good to know - Speed: on one Apple M4 Max in Chromium, the dedicated runtime reached 107 tok/s on prose. The author says speed varies with browser, hardware and prompt. - License: apache-2 - Cost to run: none named. It needs a capable GPU and the model download. - Data it reaches: the model files fetched from Hugging Face. The README says inference stays on your GPU. - Not for: long-context quality claims. The author checked that the 64K and 128K setups allocate and generate briefly, and did not run a full quality test. Decode speed on Apple M4 Max, 256 tokens | Label | Value | | --- | --- | | Prose, old runtime | 58 tok/s | | Prose, dedicated runtime | 107 tok/s | | Prose, with DSpark Auto | 104 tok/s | | JavaScript, dedicated runtime | 104 tok/s | | JavaScript, with DSpark Auto | 164 tok/s | ## README ````markdown # MiniCPM5 WebGPU Runs the MiniCPM5 2B model on your own GPU in a browser tab, to chat and to make websites, Word documents, Excel workbooks and PDFs. For people who want a local assistant with nothing to install. Made by ProCreations on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face. ## About What it is: This Space runs the MiniCPM5 2B language model on your own graphics card, inside a browser tab. You chat with it and ask it to make websites, Word documents, Excel workbooks and PDFs. It uses a purpose-built WebGPU runtime, so the model work stays on your GPU. Who it suits: It suits people who want a local chat and document assistant without installing software, and developers who want to see a model run on WebGPU. ```table Industry | Who uses it | How they use it | Example Web development | Front-end developers | Study a model running on WebGPU | Look at the runtime and its benchmark notes Office work | Anyone who drafts documents | Ask the model for a document or sheet | Request a draft workbook or a short PDF Web design | Hobby builders | Ask for a small website | Request a one-page site and review the code Research | Model researchers | Test speculative decoding in a browser | Compare the Auto, On and Off draft settings ``` You can skip it if your device has no WebGPU support or you cannot spare a multi-gigabyte download. Where to use it: - A web browser with WebGPU, on the Space's page at Hugging Face - Your own computer, on Windows, macOS or Linux, by opening the downloaded files in a browser ```table Use case | Who | What they get back Local chat | Anyone | Answers from a model that runs on your GPU Document making | Office users | Websites, Word documents, Excel workbooks and PDFs Runtime testing | Developers | A look at a WebGPU runtime and its settings ``` How to set it up: - A browser that supports WebGPU and a GPU to run it - Room for the model download, which the page puts at 3.33 GB with DSpark - Python, only if you want to download the files with the Hugging Face tool 1. Open the Space's page on Hugging Face to use it online. 2. To keep a copy, install huggingface_hub and download the Space into a folder. 3. Move into that folder. 4. In a browser, open the index.html file inside the dist folder. ```sh pip install -U huggingface_hub hf download ProCreations/minicpm5-2b-webgpu --repo-type space --local-dir minicpm5-2b-webgpu cd minicpm5-2b-webgpu ``` How to use it: Open the page, pick your settings on the launch screen, and start chatting. You can change the same settings later in model settings. The DSpark draft model has three modes. ```table Tool | What it does Auto | Measures draft cost and switches to ordinary decoding when drafting is slower On | Forces drafting with the DSpark model Off | Skips downloading and allocating DSpark ``` Example: Ask it, "Make a one-page website for a small bakery." The model writes the page code in the chat. The README notes that one generated page needed a revision, so check what you get before you use it. For newcomers and experts: If you are new, open the Space in a recent desktop browser and let the model download once. Then try a short chat before asking for a document. If you know the field, the runtime is JavaScript and WGSL for a 42-layer Llama architecture, with every layer on the GPU and no WASM inference binary. It uses Q8_0 weights, and the KV cache can be set to one of four precisions, from FP32 down to 4-bit. DSpark adds speculative decoding, where a draft model proposes up to seven tokens and the main model checks them in one pass. The author says it does not always give a speedup. ```flow The browser fetches the model files The WebGPU runtime loads them onto your GPU DSpark may draft several tokens ahead The main model checks them and streams text ``` Good to know: - Speed: on one Apple M4 Max in Chromium, the dedicated runtime reached 107 tok/s on prose. The author says speed varies with browser, hardware and prompt. - License: apache-2 - Cost to run: none named. It needs a capable GPU and the model download. - Data it reaches: the model files fetched from Hugging Face. The README says inference stays on your GPU. - Not for: long-context quality claims. The author checked that the 64K and 128K setups allocate and generate briefly, and did not run a full quality test. ```chart Title: Decode speed on Apple M4 Max, 256 tokens Prose, old runtime: 58 tok/s Prose, dedicated runtime: 107 tok/s Prose, with DSpark Auto: 104 tok/s JavaScript, dedicated runtime: 104 tok/s JavaScript, with DSpark Auto: 164 tok/s ``` ## On Hugging Face, 13 November 2026 - Likes: 9 - Built with: static - License: apache-2.0 ## Links - Space: https://huggingface.co/spaces/ProCreations/minicpm5-2b-webgpu - Files: https://huggingface.co/spaces/ProCreations/minicpm5-2b-webgpu/tree/main ## Try it Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 5 KB, downloaded as a zip. ```text README.md 5 KB ``` ## Source [ProCreations/minicpm5-2b-webgpu on Hugging Face](https://huggingface.co/spaces/ProCreations/minicpm5-2b-webgpu) ## Compare with similar Listed Hugging Face Spaces in the same category that share the most tags with this one. | Product | Likes | Built with | License | Last change | | --- | --- | --- | --- | --- | | MiniCPM5 WebGPU (this page) | 9 | static | apache-2.0 | 2026-09-11 | | [KLM 1.5-Chat Preview](https://mindket.com/p/b139ef1e-740e-407b-bcef-6e4f684014f5) | 15 | gradio | apache-2.0 | 2026-11-12 | | [DALL·E mini](https://mindket.com/p/b8ab8352-f6b8-40b8-88c6-979249c0c9a5) | 5,750 | static | apache-2.0 | 2025-08-15 | | [Kokoro Text-to-Speech (WebGPU)](https://mindket.com/p/36564f95-9b3e-4afc-b692-e8cc4e3e17b3) | 369 | static | apache-2.0 | 2025-02-07 | | [DALL·E mini by flax-community](https://mindket.com/p/e6eb151b-ffc3-43e4-bc6c-32f3d2f4d406) | 342 | static | apache-2.0 | 2022-07-19 | | [Supertonic 3 (TTS)](https://mindket.com/p/64fa85b7-db03-4d16-9519-20e7fc54c282) | 291 | static | openrail | 2026-05-18 | Numbers as Mindket last read them, on 2026-11-12. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-09-11 - First published: 2026-09-08 - Checked on Hugging Face: 2026-11-12 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open ProCreations/minicpm5-2b-webgpu on Hugging Face](https://huggingface.co/spaces/ProCreations/minicpm5-2b-webgpu) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/fece8e46-2f0f-4cd0-b12b-488e460e46ed) - [Its page on Mindket](https://mindket.com/p/fece8e46-2f0f-4cd0-b12b-488e460e46ed)