github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-23 22:21:55 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #7592] Wrong Prompt Token Report from Ignoring Image Token Count #4841

New Issue
Closed
opened 2026-04-12 15:50:25 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 15:50:25 -05:00
Owner
Copy Link

Originally created by @chigkim on GitHub (Nov 9, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7592

What is the issue?

If you run llama3.2-vision with /set verbose, it looks like it only counts tokens for text ignoring tokens from image. Thus it reports extremely slow speed for prompt rate.
It's the same with API.

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.4.0

Originally created by @chigkim on GitHub (Nov 9, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7592 ### What is the issue? If you run llama3.2-vision with /set verbose, it looks like it only counts tokens for text ignoring tokens from image. Thus it reports extremely slow speed for prompt rate. It's the same with API. ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.4.0
GiteaMirror added the bug label 2026-04-12 15:50:25 -05:00
GiteaMirror commented 2026-04-12 15:50:27 -05:00
Author
Owner
Copy Link

@jessegross commented on GitHub (Nov 11, 2024):

llama3.2-vision treats the image as a single token - it's counted, it just doesn't have a big impact on the count. Different models handle this differently and also have significantly different image processing times before they get to the language model processing stage. We count the full amount of time for accuracy but TPS will vary.

<!-- gh-comment-id:2468823095 --> @jessegross commented on GitHub (Nov 11, 2024): llama3.2-vision treats the image as a single token - it's counted, it just doesn't have a big impact on the count. Different models handle this differently and also have significantly different image processing times before they get to the language model processing stage. We count the full amount of time for accuracy but TPS will vary.
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 bug
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#4841
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?