github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 05:05:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #7794] llama3.2-vision:90b unquantized? #67037

New Issue
Closed
opened 2026-05-04 09:18:43 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-04 09:18:43 -05:00
Owner
Copy Link

Originally created by @eggsbenedicto on GitHub (Nov 22, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7794

Hi,

First of all, thanks for your work.

I tried out the llama3.2-vision:90b model on ollama and it seems to underperform the version available on the build.nvidia.com API, with the same prompt and settings. Is this because it is a quantized model? The ollama documentation on the official website says it has "Quantization Q4_K_M"

If so, is it possible to offer an un-quantized or less quantized version in ollama? I usually do AI tasks on a rented h100, so VRAM is not that much of an issue to me.

Thanks

Originally created by @eggsbenedicto on GitHub (Nov 22, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7794 Hi, First of all, thanks for your work. I tried out the llama3.2-vision:90b model on ollama and it seems to underperform the version available on the build.nvidia.com API, with the same prompt and settings. Is this because it is a quantized model? The ollama documentation on the official website says it has "Quantization Q4_K_M" If so, is it possible to offer an un-quantized or less quantized version in ollama? I usually do AI tasks on a rented h100, so VRAM is not that much of an issue to me. Thanks
GiteaMirror added the model label 2026-05-04 09:18:43 -05:00
GiteaMirror commented 2026-05-04 09:18:46 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Nov 22, 2024):

https://ollama.com/library/llama3.2-vision:90b-instruct-fp16

<!-- gh-comment-id:2493347873 --> @rick-github commented on GitHub (Nov 22, 2024): https://ollama.com/library/llama3.2-vision:90b-instruct-fp16
GiteaMirror commented 2026-05-04 09:18:47 -05:00
Author
Owner
Copy Link

@eggsbenedicto commented on GitHub (Nov 22, 2024):

Thanks! Didn't see the drop-down

<!-- gh-comment-id:2493410681 --> @eggsbenedicto commented on GitHub (Nov 22, 2024): Thanks! Didn't see the drop-down
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 model
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#67037
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?