github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #4157] Bunny-Llama-3-8B-V #64620

New Issue
Closed
opened 2026-05-03 18:21:35 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-05-03 18:21:35 -05:00
Owner
Copy Link

Originally created by @rawzone on GitHub (May 5, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4157

Would love to see: Bunny-Llama-3-8B-V included in the Ollama models.

Bunny is a family of lightweight but powerful multimodal models. It offers multiple plug-and-play vision encoders, like EVA-CLIP, SigLIP and language backbones, including Llama-3-8B, Phi-1.5, StableLM-2, Qwen1.5, MiniCPM and Phi-2. To compensate for the decrease in model size, we construct more informative training data by curated selection from a broader data source.

Originally created by @rawzone on GitHub (May 5, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4157 Would love to see: [Bunny-Llama-3-8B-V](https://huggingface.co/BAAI/Bunny-Llama-3-8B-V) included in the Ollama models. > Bunny is a family of lightweight but powerful multimodal models. It offers multiple plug-and-play vision encoders, like EVA-CLIP, SigLIP and language backbones, including Llama-3-8B, Phi-1.5, StableLM-2, Qwen1.5, MiniCPM and Phi-2. To compensate for the decrease in model size, we construct more informative training data by curated selection from a broader data source.
GiteaMirror added the model label 2026-05-03 18:21:35 -05:00
GiteaMirror commented 2026-05-03 18:21:37 -05:00
Author
Owner
Copy Link

@qhmhl commented on GitHub (May 5, 2024):

me too

<!-- gh-comment-id:2094666404 --> @qhmhl commented on GitHub (May 5, 2024): me too
GiteaMirror commented 2026-05-03 18:21:38 -05:00
Author
Owner
Copy Link

@ChaseKolozsy commented on GitHub (May 7, 2024):

I have had a chance to use Bunny through llama.cpp and it is awesome. It isn't preachy, enumerates its answers when appropriate. Seems to pick out more of the objects in the image that are present. It still hallucinates, but I don't think it hallucinates as much as the other models. That is the impression I get from it. Moreover, the LLava models on Ollama and llama.cpp seem to have to be reset/reloaded every time you use them whereas this model doesn't have to be reloaded. That is just my experience having run these models on my m3 max 128g macbook pro. I love this model simply because it is more reliable than the other models.

<!-- gh-comment-id:2099478856 --> @ChaseKolozsy commented on GitHub (May 7, 2024): I have had a chance to use Bunny through llama.cpp and it is awesome. It isn't preachy, enumerates its answers when appropriate. Seems to pick out more of the objects in the image that are present. It still hallucinates, but I don't think it hallucinates as much as the other models. That is the impression I get from it. Moreover, the LLava models on Ollama and llama.cpp seem to have to be reset/reloaded every time you use them whereas this model doesn't have to be reloaded. That is just my experience having run these models on my m3 max 128g macbook pro. I love this model simply because it is more reliable than the other models.
GiteaMirror commented 2026-05-03 18:21:38 -05:00
Author
Owner
Copy Link

@Isaachhh commented on GitHub (May 9, 2024):

Hi!
We have released GGUF format of Bunny-Llama-3-8B-V. Have a try!

https://huggingface.co/BAAI/Bunny-Llama-3-8B-V-gguf

<!-- gh-comment-id:2102251933 --> @Isaachhh commented on GitHub (May 9, 2024): Hi! We have released GGUF format of Bunny-Llama-3-8B-V. Have a try! https://huggingface.co/BAAI/Bunny-Llama-3-8B-V-gguf
GiteaMirror commented 2026-05-03 18:21:40 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 19, 2026):

$ ollama run hf.co/BAAI/Bunny-Llama-3-8B-V-gguf:Q4_K_M
>>> describe this image ./image1.jpg
Added image './image1.jpg'
This is a lovely image of a small, adorable white dog. The puppy has its ears perked up and
appears to be looking attentively towards the right side of the frame. Its head is turned
slightly towards us, giving us a view of one alert eye.
<!-- gh-comment-id:3767846494 --> @rick-github commented on GitHub (Jan 19, 2026): ```console $ ollama run hf.co/BAAI/Bunny-Llama-3-8B-V-gguf:Q4_K_M >>> describe this image ./image1.jpg Added image './image1.jpg' This is a lovely image of a small, adorable white dog. The puppy has its ears perked up and appears to be looking attentively towards the right side of the frame. Its head is turned slightly towards us, giving us a view of one alert eye. ```
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#64620
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?