github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-15 12:48:05 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #10212] request: run models directly in the browser #6699

New Issue
Open
opened 2026-04-12 18:26:03 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-12 18:26:03 -05:00
Owner
Copy Link

Originally created by @mcandre on GitHub (Apr 10, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10212

Especially for smaller models, it would be convenient and an amazing demo experience, if the main ollama website were able to cache and execute prompts against selected models, without having to install ollama or fiddle with CLI or REST components.

Perhaps there is a third party site that does this?

Originally created by @mcandre on GitHub (Apr 10, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10212 Especially for smaller models, it would be convenient and an amazing demo experience, if the main ollama website were able to cache and execute prompts against selected models, without having to install ollama or fiddle with CLI or REST components. Perhaps there is a third party site that does this?
GiteaMirror added the feature request label 2026-04-12 18:26:03 -05:00
GiteaMirror commented 2026-04-12 18:26:05 -05:00
Author
Owner
Copy Link

@JasonHonKL commented on GitHub (Apr 10, 2025):

Ollama is only for backend only.

<!-- gh-comment-id:2791681226 --> @JasonHonKL commented on GitHub (Apr 10, 2025): Ollama is only for backend only.
GiteaMirror commented 2026-04-12 18:26:05 -05:00
Author
Owner
Copy Link

@toastloaf commented on GitHub (Apr 10, 2025):

I mean, its possible and has been done before, but Ollama is for backend. WebLLM is probably what you're looking for.

<!-- gh-comment-id:2791694146 --> @toastloaf commented on GitHub (Apr 10, 2025): I mean, its possible and has been done before, but Ollama is for backend. WebLLM is probably what you're looking for.
GiteaMirror commented 2026-04-12 18:26:06 -05:00
Author
Owner
Copy Link

@mcandre commented on GitHub (Apr 10, 2025):

seems like a few lines of code would integrate the backend with the frontend

when browsing models i want the option of trying out some test prompts before deciding whether to use them with the CLI client

<!-- gh-comment-id:2793155435 --> @mcandre commented on GitHub (Apr 10, 2025): seems like a few lines of code would integrate the backend with the frontend when browsing models i want the option of trying out some test prompts before deciding whether to use them with the CLI client
GiteaMirror commented 2026-04-12 18:26:06 -05:00
Author
Owner
Copy Link

@tool2d commented on GitHub (Apr 11, 2025):

It's possible to convert phi4 to ONNX format and run it on WebGPU. However, Ollama can't do that because it lacks ONNX support.

<!-- gh-comment-id:2795832832 --> @tool2d commented on GitHub (Apr 11, 2025): It's possible to convert phi4 to ONNX format and run it on WebGPU. However, Ollama can't do that because it lacks ONNX support.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label feature request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#6699
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?