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 #13671] Please consider supporting MiroThinker-v1.5 #8981

New Issue
Closed
opened 2026-04-12 21:48:52 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 21:48:52 -05:00
Owner
Copy Link

Originally created by @asmith26 on GitHub (Jan 10, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/13671

MiroThinker is an open-source search agent model, built for tool-augmented reasoning and real-world information seeking, aiming to match the deep research experience of OpenAI Deep Research and Gemini Deep Research.

Thanks!

Originally created by @asmith26 on GitHub (Jan 10, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/13671 - https://github.com/MiroMindAI/MiroThinker - https://huggingface.co/collections/miromind-ai/mirothinker-v15 > MiroThinker is an open-source search agent model, built for tool-augmented reasoning and real-world information seeking, aiming to match the deep research experience of OpenAI Deep Research and Gemini Deep Research. Thanks!
GiteaMirror added the model label 2026-04-12 21:48:52 -05:00
GiteaMirror commented 2026-04-12 21:48:53 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 11, 2026):

This is a fine tuned qwen3 model and so can be imported.

https://huggingface.co/models?search=Mirothinker%20v1.5%20gguf

$ ollama run hf.co/mradermacher/MiroThinker-v1.5-30B-GGUF:Q4_K_M hello
pulling manifest 
pulling 6d1c5507a2ca: 100% ▕███████████████████████████████████▏  18 GB                         
pulling 2d54db2b9bb2: 100% ▕███████████████████████████████████▏ 1.5 KB                         
pulling 4a6ce91d86a8: 100% ▕███████████████████████████████████▏   99 B                         
pulling 0db680db62ea: 100% ▕███████████████████████████████████▏  561 B                         
verifying sha256 digest
writing manifest 
success 
Thinking...
The user said "hello" which is a simple greeting. I should respond warmly and appropriately. Since the user hasn't asked any specific question yet, I could:
1. Acknowledge their greeting
2. Offer assistance
3. Keep it friendly and open-ended

I should keep my response simple, friendly, and inviting to encourage further conversation.
...done thinking.

Hello! 👋 How are you today? I'm here to help if you have any questions or need assistance with anything.
<!-- gh-comment-id:3734280210 --> @rick-github commented on GitHub (Jan 11, 2026): This is a fine tuned qwen3 model and so can be [imported](https://docs.ollama.com/import#importing-a-model). https://huggingface.co/models?search=Mirothinker%20v1.5%20gguf ```console $ ollama run hf.co/mradermacher/MiroThinker-v1.5-30B-GGUF:Q4_K_M hello pulling manifest pulling 6d1c5507a2ca: 100% ▕███████████████████████████████████▏ 18 GB pulling 2d54db2b9bb2: 100% ▕███████████████████████████████████▏ 1.5 KB pulling 4a6ce91d86a8: 100% ▕███████████████████████████████████▏ 99 B pulling 0db680db62ea: 100% ▕███████████████████████████████████▏ 561 B verifying sha256 digest writing manifest success Thinking... The user said "hello" which is a simple greeting. I should respond warmly and appropriately. Since the user hasn't asked any specific question yet, I could: 1. Acknowledge their greeting 2. Offer assistance 3. Keep it friendly and open-ended I should keep my response simple, friendly, and inviting to encourage further conversation. ...done thinking. Hello! 👋 How are you today? I'm here to help if you have any questions or need assistance with anything. ```
GiteaMirror commented 2026-04-12 21:48:53 -05:00
Author
Owner
Copy Link

@asmith26 commented on GitHub (Jan 11, 2026):

Many thanks for your help @rick-github that's really helpful to know.

I'd also be interested in a cloud solution as I have limited hardware?

<!-- gh-comment-id:3734490836 --> @asmith26 commented on GitHub (Jan 11, 2026): Many thanks for your help @rick-github that's really helpful to know. I'd also be interested in a cloud solution as I have limited hardware?
GiteaMirror commented 2026-04-12 21:48:54 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 11, 2026):

Ollama Cloud has a free tier and currently offers the models listed below. If you specifically want to run MiroThinker in the cloud, you will have to rent a cloud GPU as Ollama Cloud doesn't offer the ability to run arbitrary models at the moment.

name context length quant capabilities
cogito-2.1:671b 163840 FP8 completion,thinking,tools
deepseek-v3.1:671b 163840 FP8 completion,thinking,tools
deepseek-v3.2 163840 FP8 completion,thinking,tools
devstral-2:123b 262144 FP8 completion,tools
devstral-small-2:24b 262144 FP8 completion,tools,vision
gemini-3-flash-preview 1048576 completion,thinking,tools
gemini-3-pro-preview 1048576 completion,thinking,tools,vision
gemma3:12b 131072 BF16 completion,vision
gemma3:27b 131072 BF16 completion,vision
gemma3:4b 131072 BF16 completion,vision
glm-4.6 202752 FP8 completion,thinking,tools
glm-4.7 202752 FP8 completion,thinking,tools
gpt-oss:120b 131072 MXFP4 completion,thinking,tools
gpt-oss:20b 131072 MXFP4 completion,thinking,tools
kimi-k2:1t 262144 FP8 completion,tools
kimi-k2-thinking 262144 INT4 completion,thinking,tools
minimax-m2.1 204800 FP8 completion,thinking,tools
minimax-m2 204800 completion,tools
ministral-3:14b 262144 FP8 completion,tools,vision
ministral-3:3b 262144 FP8 completion,tools,vision
ministral-3:8b 262144 FP8 completion,tools,vision
mistral-large-3:675b 262144 FP8 completion,tools,vision
nemotron-3-nano:30b 1048576 FP8 completion,thinking,tools
qwen3-coder:480b 262144 FP8 completion,tools
qwen3-next:80b 262144 FP8 completion,thinking,tools
qwen3-vl:235b 262144 BF16 completion,thinking,tools,vision
qwen3-vl:235b-instruct 262144 FP8 completion,tools,vision
rnj-1:8b 32768 FP16 completion,tools
<!-- gh-comment-id:3734827856 --> @rick-github commented on GitHub (Jan 11, 2026): [Ollama Cloud](https://ollama.com/cloud) has a free tier and currently offers the models listed below. If you specifically want to run MiroThinker in the cloud, you will have to rent a cloud GPU as Ollama Cloud doesn't offer the ability to run arbitrary models at the moment. | name |context length| quant | capabilities| | -- | -- | -- | -- | |[cogito-2.1:671b](https://ollama.com/library/cogito-2.1:671b)|163840|FP8|completion,thinking,tools| |[deepseek-v3.1:671b](https://ollama.com/library/deepseek-v3.1:671b)|163840|FP8|completion,thinking,tools| |[deepseek-v3.2](https://ollama.com/library/deepseek-v3.2)|163840|FP8|completion,thinking,tools| |[devstral-2:123b](https://ollama.com/library/devstral-2:123b)|262144|FP8|completion,tools| |[devstral-small-2:24b](https://ollama.com/library/devstral-small-2:24b)|262144|FP8|completion,tools,vision| |[gemini-3-flash-preview](https://ollama.com/library/gemini-3-flash-preview)|1048576||completion,thinking,tools| |[gemini-3-pro-preview](https://ollama.com/library/gemini-3-pro-preview)|1048576||completion,thinking,tools,vision| |[gemma3:12b](https://ollama.com/library/gemma3:12b)|131072|BF16|completion,vision| |[gemma3:27b](https://ollama.com/library/gemma3:27b)|131072|BF16|completion,vision| |[gemma3:4b](https://ollama.com/library/gemma3:4b)|131072|BF16|completion,vision| |[glm-4.6](https://ollama.com/library/glm-4.6)|202752|FP8|completion,thinking,tools| |[glm-4.7](https://ollama.com/library/glm-4.7)|202752|FP8|completion,thinking,tools| |[gpt-oss:120b](https://ollama.com/library/gpt-oss:120b)|131072|MXFP4|completion,thinking,tools| |[gpt-oss:20b](https://ollama.com/library/gpt-oss:20b)|131072|MXFP4|completion,thinking,tools| |[kimi-k2:1t](https://ollama.com/library/kimi-k2:1t)|262144|FP8|completion,tools| |[kimi-k2-thinking](https://ollama.com/library/kimi-k2-thinking)|262144|INT4|completion,thinking,tools| |[minimax-m2.1](https://ollama.com/library/minimax-m2.1)|204800|FP8|completion,thinking,tools| |[minimax-m2](https://ollama.com/library/minimax-m2)|204800||completion,tools| |[ministral-3:14b](https://ollama.com/library/ministral-3:14b)|262144|FP8|completion,tools,vision| |[ministral-3:3b](https://ollama.com/library/ministral-3:3b)|262144|FP8|completion,tools,vision| |[ministral-3:8b](https://ollama.com/library/ministral-3:8b)|262144|FP8|completion,tools,vision| |[mistral-large-3:675b](https://ollama.com/library/mistral-large-3:675b)|262144|FP8|completion,tools,vision| |[nemotron-3-nano:30b](https://ollama.com/library/nemotron-3-nano:30b)|1048576|FP8|completion,thinking,tools| |[qwen3-coder:480b](https://ollama.com/library/qwen3-coder:480b)|262144|FP8|completion,tools| |[qwen3-next:80b](https://ollama.com/library/qwen3-next:80b)|262144|FP8|completion,thinking,tools| |[qwen3-vl:235b](https://ollama.com/library/qwen3-vl:235b)|262144|BF16|completion,thinking,tools,vision| |[qwen3-vl:235b-instruct](https://ollama.com/library/qwen3-vl:235b-instruct)|262144|FP8|completion,tools,vision| |[rnj-1:8b](https://ollama.com/library/rnj-1:8b)|32768|FP16|completion,tools|
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#8981
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?