github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-21 13:11:39 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[PR #10708] [MERGED] feat: qwen3 dense and sparse models #18606

New Issue
Closed
opened 2026-04-16 06:40:45 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-16 06:40:45 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/10708
Author: @mxyng
Created: 5/14/2025
Status: ✅ Merged
Merged: 5/21/2025
Merged by: @mxyng

Base: main ← Head: mxyng/qwen3

📝 Commits (3)

📊 Changes

5 files changed (+258 additions, -1 deletions)

View changed files

📝 ml/backend.go (+3 -0)
📝 ml/backend/ggml/ggml.go (+14 -0)
📝 model/models/llama4/model_text.go (+1 -1)
📝 model/models/models.go (+1 -0)
➕ model/models/qwen3/model.go (+239 -0)

📄 Description

this change adds Qwen 3 model family to the Ollama engine. It supports both the dense models as well as the sparse, mixture of experts models

dense:

mixture of experts:

This change works for all existing models found in library/qwen3

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/ollama/ollama/pull/10708 **Author:** [@mxyng](https://github.com/mxyng) **Created:** 5/14/2025 **Status:** ✅ Merged **Merged:** 5/21/2025 **Merged by:** [@mxyng](https://github.com/mxyng) **Base:** `main` ← **Head:** `mxyng/qwen3` --- ### 📝 Commits (3) - [`96d07fb`](https://github.com/ollama/ollama/commit/96d07fba36f880092d06e5d24331fe998ca4ffd4) feat: qwen3 dense - [`b4b3ee4`](https://github.com/ollama/ollama/commit/b4b3ee4dcb13c6be6705a8dbc81cc11b1a98d848) feat: qwen3moe - [`555e63f`](https://github.com/ollama/ollama/commit/555e63f2bb4df667c02d86e02db2db24798aa800) fix llama4 moe ### 📊 Changes **5 files changed** (+258 additions, -1 deletions) <details> <summary>View changed files</summary> 📝 `ml/backend.go` (+3 -0) 📝 `ml/backend/ggml/ggml.go` (+14 -0) 📝 `model/models/llama4/model_text.go` (+1 -1) 📝 `model/models/models.go` (+1 -0) ➕ `model/models/qwen3/model.go` (+239 -0) </details> ### 📄 Description this change adds Qwen 3 model family to the Ollama engine. It supports both the dense models as well as the sparse, mixture of experts models dense: - [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) - [Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B) - [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B) - [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) - [Qwen/Qwen3-14B](https://huggingface.co/Qwen/Qwen3-14B) - [Qwen/Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B) mixture of experts: - [Qwen/Qwen3-30B-A3B](https://huggingface.co/Qwen/Qwen3-30B-A3B) - [Qwen/Qwen3-235B-A22B](https://huggingface.co/Qwen/Qwen3-235B-A22B) This change works for all existing models found in [library/qwen3](https://ollama.com/library/qwen3) --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
GiteaMirror added the pull-request label 2026-04-16 06:40:45 -05:00
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 pull-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#18606
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?