github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 13:19:40 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #9871] Gemma3-12b: 8K context window or 128K? #84149

New Issue
Closed
opened 2026-05-09 20:03:32 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-09 20:03:32 -05:00
Owner
Copy Link

Originally created by @mswcap on GitHub (Mar 18, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9871

Hi all.

First of all compliments for Ollama, It's great software and I like it. The webpage for Gemma3-12 b states that the context window is 128K:

Gemma is a lightweight, family of models from Google built on Gemini technology. The Gemma 3 models are multimodal—processing text and images—and feature a 128K context window with support for over 140 languages. Available in 1B, 4B, 12B, and 27B parameter sizes, they excel in tasks like question answering, summarization, and reasoning, while their compact design allows deployment on resource-limited devices.

However, when I have installed the Gemma3-12b model, this is what Ollama states:

ollama show gemma3:12b
Model
architecture gemma3
parameters 12.2B
context length 8192 (8K)
embedding length 3840
quantization Q4_K_M
Parameters
stop "<end_of_turn>"
temperature 0.1
License
Gemma Terms of Use
Last modified: February 21, 2024

So the context window is 8K. The model still performs impressive, but can someone explain the 'missing' 120K context window?I only want to learn and understand. And again, I think Gemma3-12b is a great LLM, performing wonderful on everyday hardware.

With kind regards
MW

Originally created by @mswcap on GitHub (Mar 18, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9871 Hi all. First of all compliments for Ollama, It's great software and I like it. The [webpage for Gemma3-12 b](https://ollama.com/library/gemma3) states that the context window is 128K: > Gemma is a lightweight, family of models from Google built on Gemini technology. The Gemma 3 models are multimodal—processing text and images—and feature a 128K context window with support for over 140 languages. Available in 1B, 4B, 12B, and 27B parameter sizes, they excel in tasks like question answering, summarization, and reasoning, while their compact design allows deployment on resource-limited devices. However, when I have installed the Gemma3-12b model, this is what Ollama states: > ollama show gemma3:12b Model architecture gemma3 parameters 12.2B context length **8192** (8K) embedding length 3840 quantization Q4_K_M Parameters stop "<end_of_turn>" temperature 0.1 License Gemma Terms of Use Last modified: February 21, 2024 So the context window is 8K. The model still performs impressive, but can someone explain the 'missing' 120K context window?I only want to learn and understand. And again, I think Gemma3-12b is a great LLM, performing wonderful on everyday hardware. With kind regards MW
GiteaMirror commented 2026-05-09 20:03:35 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 18, 2025):

https://github.com/ollama/ollama/issues/9702#issuecomment-2722840055

<!-- gh-comment-id:2734828305 --> @rick-github commented on GitHub (Mar 18, 2025): https://github.com/ollama/ollama/issues/9702#issuecomment-2722840055
GiteaMirror commented 2026-05-09 20:03:36 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Mar 18, 2025):

Going to go ahead and close this.

<!-- gh-comment-id:2734890604 --> @pdevine commented on GitHub (Mar 18, 2025): Going to go ahead and close this.
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
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#84149
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?