[GH-ISSUE #10970] Support for MedGemma #7229

New Issue

GiteaMirror · 2026-04-12T19:14:25-05:00

GiteaMirror commented

2026-04-12 19:14:25 -05:00

Originally created by @fighter3005 on GitHub (Jun 4, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10970

Hi, I would love to run MedGemma (4B with vision is broken for me) on my local WebUI! Since Gemma3 is supported, this might actually be easy?

Originally created by @fighter3005 on GitHub (Jun 4, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10970 Hi, I would love to run MedGemma (4B with vision is broken for me) on my local WebUI! Since Gemma3 is supported, this might actually be easy?

GiteaMirror added the model label 2026-04-12 19:14:25 -05:00

GiteaMirror commented

2026-04-12 19:14:27 -05:00

@matrix07012 commented on GitHub (Jun 8, 2025):

For some reason the quantizations from HF don't work with vision. You have to download full fp16 version of the model and either use that or quantize it yourself with ollama create -q q8_0 model

@matrix07012 commented on GitHub (Jun 8, 2025): For some reason the quantizations from HF don't work with vision. You have to download full fp16 version of the model and either use that or quantize it yourself with `ollama create -q q8_0 model`

GiteaMirror commented

2026-04-12 19:14:28 -05:00

@fighter3005 commented on GitHub (Jun 10, 2025):

The model does run, but it seems that image encoder is not part of the model weights!? I am not sure what is going on there. I get:
level=INFO source=server.go:809 msg="llm predict error: Failed to create new sequence: failed to process inputs: this model is missing data required for image input".

@fighter3005 commented on GitHub (Jun 10, 2025): The model does run, but it seems that image encoder is not part of the model weights!? I am not sure what is going on there. I get: `level=INFO source=server.go:809 msg="llm predict error: Failed to create new sequence: failed to process inputs: this model is missing data required for image input"`.

GiteaMirror commented

2026-04-12 19:14:29 -05:00

@pupphelper commented on GitHub (Jun 11, 2025):

For some reason the quantizations from HF don't work with vision. You have to download full fp16 version of the model and either use that or quantize it yourself with ollama create -q q8_0 model

which fp16 model works? can you link it? I tried some F16 GGUF same problem, I'm having the same issue, vison not working on openwebui

@pupphelper commented on GitHub (Jun 11, 2025): > For some reason the quantizations from HF don't work with vision. You have to download full fp16 version of the model and either use that or quantize it yourself with `ollama create -q q8_0 model` which fp16 model works? can you link it? I tried some F16 GGUF same problem, I'm having the same issue, vison not working on openwebui

GiteaMirror commented

2026-04-12 19:14:30 -05:00

@matrix07012 commented on GitHub (Jun 12, 2025):

For some reason the quantizations from HF don't work with vision. You have to download full fp16 version of the model and either use that or quantize it yourself with ollama create -q q8_0 model

which fp16 model works? can you link it? I tried some F16 GGUF same problem, I'm having the same issue, vison not working on openwebui

Not GGUF, the original safetensor version straight from Google

@matrix07012 commented on GitHub (Jun 12, 2025): > > For some reason the quantizations from HF don't work with vision. You have to download full fp16 version of the model and either use that or quantize it yourself with `ollama create -q q8_0 model` > > which fp16 model works? can you link it? I tried some F16 GGUF same problem, I'm having the same issue, vison not working on openwebui Not GGUF, the original safetensor version straight from Google

GiteaMirror commented

2026-04-12 19:14:31 -05:00

@amsaravi commented on GitHub (Jun 13, 2025):

@fighter3005 I created model for you. you can find it here:
https://ollama.com/amsaravi/medgemma-4b-it-q8

take a look at this notebook to see how to do that:
https://colab.research.google.com/drive/12MW3bwp_-rXVFuC_6dVBp9q8VPCvVFT7?usp=sharing

@amsaravi commented on GitHub (Jun 13, 2025): @fighter3005 I created model for you. you can find it here: https://ollama.com/amsaravi/medgemma-4b-it-q8 take a look at this notebook to see how to do that: https://colab.research.google.com/drive/12MW3bwp_-rXVFuC_6dVBp9q8VPCvVFT7?usp=sharing

GiteaMirror commented

2026-04-12 19:14:32 -05:00

@fighter3005 commented on GitHub (Jun 16, 2025):

@fighter3005 I created model for you. you can find it here: https://ollama.com/amsaravi/medgemma-4b-it-q8

take a look at this notebook to see how to do that: https://colab.research.google.com/drive/12MW3bwp_-rXVFuC_6dVBp9q8VPCvVFT7?usp=sharing

Thank you for the nice tutorial & the Model! However, if I just pull your model and run it in open webui, I get gibberish. Do I need to set something in the Modelfile? Or do I need to create one?

<unused22><unused22><unused5><unused1><unused12><unused26>[multimodal]<unused16><unused18><unused10><unused22><unused31>

@fighter3005 commented on GitHub (Jun 16, 2025): > [@fighter3005](https://github.com/fighter3005) I created model for you. you can find it here: https://ollama.com/amsaravi/medgemma-4b-it-q8 > > take a look at this notebook to see how to do that: https://colab.research.google.com/drive/12MW3bwp_-rXVFuC_6dVBp9q8VPCvVFT7?usp=sharing Thank you for the nice tutorial & the Model! However, if I just pull your model and run it in open webui, I get gibberish. Do I need to set something in the Modelfile? Or do I need to create one? `<unused22><unused22><unused5><unused1><unused12><unused26>[multimodal]<unused16><unused18><unused10><unused22><unused31>`

GiteaMirror commented

2026-04-12 19:14:33 -05:00

@amsaravi commented on GitHub (Jun 29, 2025):

i am working on it. perhaps the templates must be updated. stay tuned!

@amsaravi commented on GitHub (Jun 29, 2025): i am working on it. perhaps the templates must be updated. stay tuned!

GiteaMirror commented

2026-04-12 19:14:34 -05:00

@amsaravi commented on GitHub (Jun 30, 2025):

I recreated the model using ollama 0.6.2. text prompt works. I've no time to test if image support works as well. plz give me feedback.
https://ollama.com/amsaravi/medgemma-4b-it
ollama run amsaravi/medgemma-4b-it:q8

@amsaravi commented on GitHub (Jun 30, 2025): I recreated the model using ollama 0.6.2. text prompt works. I've no time to test if image support works as well. plz give me feedback. https://ollama.com/amsaravi/medgemma-4b-it `ollama run amsaravi/medgemma-4b-it:q8`

GiteaMirror commented

2026-04-12 19:14:35 -05:00

@amsaravi commented on GitHub (Jul 1, 2025):

i have tested on ollama 0.9.0. image and text, both of them works

@amsaravi commented on GitHub (Jul 1, 2025): i have tested on ollama 0.9.0. image and text, both of them works

GiteaMirror commented

2026-04-12 19:14:36 -05:00

@fighter3005 commented on GitHub (Jul 7, 2025):

i have tested on ollama 0.9.0. image and text, both of them works

Thank you very much! Works!

@fighter3005 commented on GitHub (Jul 7, 2025): > i have tested on ollama 0.9.0. image and text, both of them works Thank you very much! Works!

GiteaMirror commented

2026-04-12 19:14:37 -05:00

@XwK-P commented on GitHub (Jul 11, 2025):

i have tested on ollama 0.9.0. image and text, both of them works

@amsaravi Thanks for your work. I noticed that the multi modal 27B version of medgemma was released. https://huggingface.co/google/medgemma-27b-it
If you don't mind, could you please create the ollama model for 27b as well?

Edit:
I've created it myself.
https://ollama.com/puyangwang/medgemma-27b-it

@XwK-P commented on GitHub (Jul 11, 2025): > i have tested on ollama 0.9.0. image and text, both of them works @amsaravi Thanks for your work. I noticed that the multi modal 27B version of medgemma was released. https://huggingface.co/google/medgemma-27b-it If you don't mind, could you please create the ollama model for 27b as well? Edit: I've created it myself. https://ollama.com/puyangwang/medgemma-27b-it

GiteaMirror commented

2026-04-12 19:14:38 -05:00

@illusdolphin commented on GitHub (Jul 14, 2025):

i have tested on ollama 0.9.0. image and text, both of them works

@amsaravi Thanks for your work. I noticed that the multi modal 27B version of medgemma was released. https://huggingface.co/google/medgemma-27b-it If you don't mind, could you please create the ollama model for 27b as well?

Edit: I've created it myself. https://ollama.com/puyangwang/medgemma-27b-it

May I ask you go add also Q4 version?

@illusdolphin commented on GitHub (Jul 14, 2025): > > i have tested on ollama 0.9.0. image and text, both of them works > > [@amsaravi](https://github.com/amsaravi) Thanks for your work. I noticed that the multi modal 27B version of medgemma was released. https://huggingface.co/google/medgemma-27b-it If you don't mind, could you please create the ollama model for 27b as well? > > Edit: I've created it myself. https://ollama.com/puyangwang/medgemma-27b-it May I ask you go add also Q4 version?

GiteaMirror commented

2026-04-12 19:14:39 -05:00

@XwK-P commented on GitHub (Jul 14, 2025):

i have tested on ollama 0.9.0. image and text, both of them works

@amsaravi Thanks for your work. I noticed that the multi modal 27B version of medgemma was released. https://huggingface.co/google/medgemma-27b-it If you don't mind, could you please create the ollama model for 27b as well?
Edit: I've created it myself. https://ollama.com/puyangwang/medgemma-27b-it

May I ask you go add also Q4 version?

Q4_0 and Q4_K_M uploaded.
https://ollama.com/puyangwang/medgemma-27b-it/tags

@XwK-P commented on GitHub (Jul 14, 2025): > > > i have tested on ollama 0.9.0. image and text, both of them works > > > > > > [@amsaravi](https://github.com/amsaravi) Thanks for your work. I noticed that the multi modal 27B version of medgemma was released. https://huggingface.co/google/medgemma-27b-it If you don't mind, could you please create the ollama model for 27b as well? > > Edit: I've created it myself. https://ollama.com/puyangwang/medgemma-27b-it > > May I ask you go add also Q4 version? Q4_0 and Q4_K_M uploaded. https://ollama.com/puyangwang/medgemma-27b-it/tags

GiteaMirror commented

2026-04-12 19:14:40 -05:00

@illusdolphin commented on GitHub (Jul 14, 2025):

Thank you very much!

@illusdolphin commented on GitHub (Jul 14, 2025): Thank you very much!

GiteaMirror commented

2026-04-12 19:14:41 -05:00

@yenjia commented on GitHub (Jul 29, 2025):

i have tested on ollama 0.9.0. image and text, both of them works

@amsaravi Thanks for your work. I noticed that the multi modal 27B version of medgemma was released. https://huggingface.co/google/medgemma-27b-it If you don't mind, could you please create the ollama model for 27b as well?

Edit: I've created it myself. https://ollama.com/puyangwang/medgemma-27b-it

Hi. I'm curious how to create the quantized ollama model. I tried different ways, and I got weird results after quantizing the model. Thank you!

@yenjia commented on GitHub (Jul 29, 2025): > > i have tested on ollama 0.9.0. image and text, both of them works > > [@amsaravi](https://github.com/amsaravi) Thanks for your work. I noticed that the multi modal 27B version of medgemma was released. https://huggingface.co/google/medgemma-27b-it If you don't mind, could you please create the ollama model for 27b as well? > > Edit: I've created it myself. https://ollama.com/puyangwang/medgemma-27b-it Hi. I'm curious how to create the quantized ollama model. I tried different ways, and I got weird results after quantizing the model. Thank you!

GiteaMirror commented

2026-04-12 19:14:41 -05:00

@XwK-P commented on GitHub (Jul 29, 2025):

i have tested on ollama 0.9.0. image and text, both of them works

@amsaravi Thanks for your work. I noticed that the multi modal 27B version of medgemma was released. https://huggingface.co/google/medgemma-27b-it If you don't mind, could you please create the ollama model for 27b as well?
Edit: I've created it myself. https://ollama.com/puyangwang/medgemma-27b-it

Hi. I'm curious how to create the quantized ollama model. I tried different ways, and I got weird results after quantizing the model. Thank you!

Need to downgrade Ollama to 0.6.2 for quantization. Quantized model will still work with latest Ollama.

@XwK-P commented on GitHub (Jul 29, 2025): > > > i have tested on ollama 0.9.0. image and text, both of them works > > > > > > [@amsaravi](https://github.com/amsaravi) Thanks for your work. I noticed that the multi modal 27B version of medgemma was released. https://huggingface.co/google/medgemma-27b-it If you don't mind, could you please create the ollama model for 27b as well? > > Edit: I've created it myself. https://ollama.com/puyangwang/medgemma-27b-it > > Hi. I'm curious how to create the quantized ollama model. I tried different ways, and I got weird results after quantizing the model. Thank you! Need to downgrade Ollama to 0.6.2 for quantization. Quantized model will still work with latest Ollama.

GiteaMirror commented

2026-04-12 19:14:43 -05:00

@yenjia commented on GitHub (Jul 29, 2025):

i have tested on ollama 0.9.0. image and text, both of them works

@amsaravi Thanks for your work. I noticed that the multi modal 27B version of medgemma was released. https://huggingface.co/google/medgemma-27b-it If you don't mind, could you please create the ollama model for 27b as well?
Edit: I've created it myself. https://ollama.com/puyangwang/medgemma-27b-it

Hi. I'm curious how to create the quantized ollama model. I tried different ways, and I got weird results after quantizing the model. Thank you!

Need to downgrade Ollama to 0.6.2 for quantization. Quantized model will still work with latest Ollama.

Thank you very much!

@yenjia commented on GitHub (Jul 29, 2025): > > > > i have tested on ollama 0.9.0. image and text, both of them works > > > > > > > > > [@amsaravi](https://github.com/amsaravi) Thanks for your work. I noticed that the multi modal 27B version of medgemma was released. https://huggingface.co/google/medgemma-27b-it If you don't mind, could you please create the ollama model for 27b as well? > > > Edit: I've created it myself. https://ollama.com/puyangwang/medgemma-27b-it > > > > > > Hi. I'm curious how to create the quantized ollama model. I tried different ways, and I got weird results after quantizing the model. Thank you! > > Need to downgrade Ollama to 0.6.2 for quantization. Quantized model will still work with latest Ollama. Thank you very much!

GiteaMirror commented

2026-04-12 19:14:43 -05:00

@OdinVex commented on GitHub (Sep 22, 2025):

I was running medgemma-27b-text-it:latest (134e...) from Ollama successfully and it's been a while since, but now it generates gibberish. Has something changed, any way to diagnose?

@OdinVex commented on GitHub (Sep 22, 2025): I was running `medgemma-27b-text-it:latest` (`134e...`) from Ollama successfully and it's been a while since, but now it generates gibberish. Has something changed, any way to diagnose?

GiteaMirror commented

2026-04-12 19:14:44 -05:00

@njpogue commented on GitHub (Sep 23, 2025):

I am also trying to run medgemma-4b-it on ollama server from this HF repo (https://huggingface.co/SandLogicTechnologies/MedGemma-4B-IT-GGUF/blob/main/medgemma-4b-it-Q5_K_M.gguf), but does not appear to work. When I pass cURL command with "images" parameter in base64 format, I also get Failed to create new sequence: failed to process inputs: this model is missing data required for image input"

@njpogue commented on GitHub (Sep 23, 2025): I am also trying to run medgemma-4b-it on ollama server from this HF repo (https://huggingface.co/SandLogicTechnologies/MedGemma-4B-IT-GGUF/blob/main/medgemma-4b-it-Q5_K_M.gguf), but does not appear to work. When I pass cURL command with "images" parameter in base64 format, I also get `Failed to create new sequence: failed to process inputs: this model is missing data required for image input"`

GiteaMirror commented

2026-04-12 19:14:45 -05:00

@code-forge-temple commented on GitHub (Jan 13, 2026):

Hi! Are there any new updates on the status of this issue? Has there been any progress toward MedGemma multimodal support or a timeline for resolving it?

@code-forge-temple commented on GitHub (Jan 13, 2026): Hi! Are there any new updates on the status of this issue? Has there been any progress toward MedGemma multimodal support or a timeline for resolving it?

GiteaMirror commented

2026-04-12 19:14:46 -05:00

@illusdolphin commented on GitHub (Jan 14, 2026):

Hi! Are there any new updates on the status of this issue? Has there been any progress toward MedGemma multimodal support or a timeline for resolving it?

What is not working? It's working for a long time already, use https://ollama.com/puyangwang/medgemma-27b-it for vision

@illusdolphin commented on GitHub (Jan 14, 2026): > Hi! Are there any new updates on the status of this issue? Has there been any progress toward MedGemma multimodal support or a timeline for resolving it? What is not working? It's working for a long time already, use https://ollama.com/puyangwang/medgemma-27b-it for vision

GiteaMirror commented

2026-04-12 19:14:46 -05:00

@OdinVex commented on GitHub (Jan 14, 2026):

Hi! Are there any new updates on the status of this issue? Has there been any progress toward MedGemma multimodal support or a timeline for resolving it?

What is not working? It's working for a long time already, use https://ollama.com/puyangwang/medgemma-27b-it for vision

This is MedGemma-27b-it, not some random upload: https://huggingface.co/google/medgemma-27b-it/tree/main That random upload you referenced is the one sometimes spitting out gibberish.

@OdinVex commented on GitHub (Jan 14, 2026): > > Hi! Are there any new updates on the status of this issue? Has there been any progress toward MedGemma multimodal support or a timeline for resolving it? > > What is not working? It's working for a long time already, use https://ollama.com/puyangwang/medgemma-27b-it for vision *This* is MedGemma-27b-it, not some random upload: https://huggingface.co/google/medgemma-27b-it/tree/main That random upload you referenced is the one sometimes spitting out gibberish.

GiteaMirror commented

2026-04-12 19:14:47 -05:00

@code-forge-temple commented on GitHub (Jan 14, 2026):

@illusdolphin Apologies for not providing more details earlier - thanks for the pointer.

I was referring specifically to Google's official MedGemma published on Hugging Face, for example:
https://huggingface.co/google/medgemma-1.5-4b-it or the full list (https://huggingface.co/collections/google/medgemma-release)

My understanding is that this model has a different multimodal architecture compared to the community-converted Ollama versions. It would be extraordinary if Ollama could directly support Hugging Face MedGemma models (including both text and vision) without requiring custom conversions.

@code-forge-temple commented on GitHub (Jan 14, 2026): @illusdolphin Apologies for not providing more details earlier - thanks for the pointer. I was referring specifically to **Google's official MedGemma published on Hugging Face**, for example: https://huggingface.co/google/medgemma-1.5-4b-it or the full list (https://huggingface.co/collections/google/medgemma-release) My understanding is that this model has a different multimodal architecture compared to the community-converted Ollama versions. It would be extraordinary if Ollama could directly support Hugging Face MedGemma models (including both text and vision) without requiring custom conversions.

GiteaMirror commented

2026-04-12 19:14:48 -05:00

@illusdolphin commented on GitHub (Jan 14, 2026):

@illusdolphin Apologies for not providing more details earlier - thanks for the pointer.

I was referring specifically to Google's official MedGemma published on Hugging Face, for example: https://huggingface.co/google/medgemma-1.5-4b-it or the full list (https://huggingface.co/collections/google/medgemma-release)

My understanding is that this model has a different multimodal architecture compared to the community-converted Ollama versions. It would be extraordinary if Ollama could directly support Hugging Face MedGemma models (including both text and vision) without requiring custom conversions.

Google published models using safetensors format, ollama works with GGUF (also safe, but other format). safetensors => GGUF is just change of format, not weight, not quality. You can't use https://huggingface.co/google/medgemma-1.5-4b-it link since it has no files in format that ollama expects. Options are: 1) beg for official GGUF-based release (don't think it makes sense) 2) do it by yourself 3) use GGUF published by other users

@illusdolphin commented on GitHub (Jan 14, 2026): > [@illusdolphin](https://github.com/illusdolphin) Apologies for not providing more details earlier - thanks for the pointer. > > I was referring specifically to **Google's official MedGemma published on Hugging Face**, for example: https://huggingface.co/google/medgemma-1.5-4b-it or the full list (https://huggingface.co/collections/google/medgemma-release) > > My understanding is that this model has a different multimodal architecture compared to the community-converted Ollama versions. It would be extraordinary if Ollama could directly support Hugging Face MedGemma models (including both text and vision) without requiring custom conversions. Google published models using safetensors format, ollama works with GGUF (also safe, but other format). safetensors => GGUF is just change of format, not weight, not quality. You can't use https://huggingface.co/google/medgemma-1.5-4b-it link since it has no files in format that ollama expects. Options are: 1) beg for official GGUF-based release (don't think it makes sense) 2) do it by yourself 3) use GGUF published by other users

GiteaMirror commented

2026-04-12 19:14:49 -05:00

@OdinVex commented on GitHub (Jan 14, 2026):

@illusdolphin Apologies for not providing more details earlier - thanks for the pointer.
I was referring specifically to Google's official MedGemma published on Hugging Face, for example: https://huggingface.co/google/medgemma-1.5-4b-it or the full list (https://huggingface.co/collections/google/medgemma-release)
My understanding is that this model has a different multimodal architecture compared to the community-converted Ollama versions. It would be extraordinary if Ollama could directly support Hugging Face MedGemma models (including both text and vision) without requiring custom conversions.

Google published models using safetensors format, ollama works with GGUF (also safe, but other format). safetensors => GGUF is just change of format, not weight, not quality. You can't use https://huggingface.co/google/medgemma-1.5-4b-it link since it has no files in format that ollama expects. Options are: 1) beg for official GGUF-based release (don't think it makes sense) 2) do it by yourself 3) use GGUF published by other users

Ollama partly works with GGUF. It still doesn't support split GGUF models. As for puyangwang/medgemma-27b-it, it started generating gibberish, so no thanks.

@OdinVex commented on GitHub (Jan 14, 2026): > > [@illusdolphin](https://github.com/illusdolphin) Apologies for not providing more details earlier - thanks for the pointer. > > I was referring specifically to **Google's official MedGemma published on Hugging Face**, for example: https://huggingface.co/google/medgemma-1.5-4b-it or the full list (https://huggingface.co/collections/google/medgemma-release) > > My understanding is that this model has a different multimodal architecture compared to the community-converted Ollama versions. It would be extraordinary if Ollama could directly support Hugging Face MedGemma models (including both text and vision) without requiring custom conversions. > > Google published models using safetensors format, ollama works with GGUF (also safe, but other format). safetensors => GGUF is just change of format, not weight, not quality. You can't use https://huggingface.co/google/medgemma-1.5-4b-it link since it has no files in format that ollama expects. Options are: 1) beg for official GGUF-based release (don't think it makes sense) 2) do it by yourself 3) use GGUF published by other users Ollama *partly* works with GGUF. It *still* doesn't support split GGUF models. As for `puyangwang/medgemma-27b-it`, it started generating gibberish, so no thanks.

GiteaMirror referenced this issue

2026-04-12 23:56:43 -05:00

[PR #7229] [CLOSED] Move Go code out of llm package #12358

GiteaMirror referenced this issue

2026-04-16 06:09:09 -05:00

[PR #7229] [CLOSED] Move Go code out of llm package #17629

GiteaMirror referenced this issue

2026-04-19 16:38:09 -05:00

[PR #7229] [CLOSED] Move Go code out of llm package #22898

GiteaMirror referenced this issue

2026-04-22 22:54:14 -05:00

[PR #7229] [CLOSED] Move Go code out of llm package #38231

GiteaMirror referenced this issue

2026-04-24 23:12:56 -05:00

[PR #7229] [CLOSED] Move Go code out of llm package #43606

GiteaMirror referenced this issue

2026-04-29 13:56:08 -05:00

[PR #7229] [CLOSED] Move Go code out of llm package #59055

GiteaMirror referenced this issue

2026-05-05 06:52:16 -05:00

[PR #7229] [CLOSED] Move Go code out of llm package #74652

Sign in to join this conversation.

Branches Tags

main

dhiltgen/ci

dhiltgen/llama-runner

parth-launch-codex-app

hoyyeva/anthropic-local-image-path

hoyyeva/anthropic-reference-images-path

parth-anthropic-reference-images-path

brucemacd/download-before-remove

hoyyeva/editor-config-repair

parth-mlx-decode-checkpoints

hoyyeva/fix-codex-model-metadata-warning

hoyyeva/qwen

parth/hide-claude-desktop-till-release

hoyyeva/opencode-image-modality

parth-add-claude-code-autoinstall

release_v0.22.0

pdevine/manifest-list

codex/fix-codex-model-metadata-warning

pdevine/addressable-manifest

brucemacd/launch-fetch-reccomended

jmorganca/llama-compat

launch-copilot-cli

hoyyeva/opencode-thinking

release_v0.20.7

parth-auto-save-backup

parth-test

jmorganca/gemma4-audio-replacements

fix-manifest-digest-on-pull

hoyyeva/vscode-improve

brucemacd/install-server-wait

parth/update-claude-docs

brucemac/start-ap-install

pdevine/mlx-update

pdevine/qwen35_vision

drifkin/api-show-fallback

mintlify/image-generation-1773352582

hoyyeva/server-context-length-local-config

jmorganca/faster-reptition-penalties

jmorganca/convert-nemotron

parth-pi-thinking

pdevine/sampling-penalties

jmorganca/fix-create-quantization-memory

dongchen/resumable_transfer_fix

pdevine/sampling-cache-error

jessegross/mlx-usage

hoyyeva/openclaw-config

hoyyeva/app-html

pdevine/qwen3next

brucemacd/sign-sh-install

brucemacd/tui-update

brucemacd/usage-api

jmorganca/launch-empty

fix-app-dist-embed

mxyng/mlx-compile

mxyng/mlx-quant

mxyng/mlx-glm4.7

mxyng/mlx

brucemacd/simplify-model-picker

jmorganca/qwen3-concurrent

fix-glm-4.7-flash-mla-config

drifkin/qwen3-coder-opening-tag

brucemacd/usage-cli

fix-cuda12-fattn-shmem

ollama-imagegen-docs

parth/fix-multiline-inputs

brucemacd/config-docs

mxyng/model-files

mxyng/simple-execute

fix-imagegen-ollama-models

mxyng/async-upload

jmorganca/lazy-no-dtype-changes

imagegen-auto-detect-create

parth/decrease-concurrent-download-hf

fix-mlx-quantize-init

jmorganca/x-cleanup

usage

imagegen-readme

jmorganca/glm-image

mlx-gpu-cd

jmorganca/imagegen-modelfile

parth/agent-skills

parth/agent-allowlist

parth/signed-in-offline

parth/agents

parth/fix-context-chopping

improve-cloud-flow

parth/add-models-websearch

parth/prompt-renderer-mcp

jmorganca/native-settings

jmorganca/download-stream-hash

jmorganca/client2-rebased

brucemacd/oai-chat-req-multipart

jessegross/multi_chunk_reserve

grace/additional-omit-empty

grace/mistral-3-large

mxyng/tokenizer2

mxyng/tokenizer

jessegross/flash

hoyyeva/windows-nacked-app

mxyng/cleanup-attention

grace/deepseek-parser

hoyyeva/remember-unsent-prompt

parth/add-lfs-pointer-error-conversion

parth/olmo2-test2

hoyyeva/ollama-launchagent-plist

nicole/olmo-model

parth/olmo-test

mxyng/remove-embedded

parth/render-template

jmorganca/intellect-3

parth/remove-prealloc-linter

jmorganca/cmd-eval

nicole/nomic-embed-text-fix

mxyng/lint-2

hoyyeva/add-gemini-3-pro-preview

hoyyeva/load-model-list

mxyng/expand-path

mxyng/environ-2

hoyyeva/deeplink-json-encoding

parth/improve-tool-calling-tests

hoyyeva/conversation

hoyyeva/assistant-edit-response

hoyyeva/thinking

origin/brucemacd/invalid-char-i-err

parth/improve-tool-calling

jmorganca/required-omitempty

grace/qwen3-vl-tests

mxyng/iter-client

parth/docs-readme

nicole/embed-test

pdevine/integration-benchstat

parth/remove-generate-cmd

parth/add-toolcall-id

mxyng/server-tests

jmorganca/glm-4.6

jmorganca/gin-h-compat

drifkin/stable-tool-args

pdevine/qwen3-more-thinking

parth/add-websearch-client

nicole/websearch_local

jmorganca/qwen3-coder-updates

grace/deepseek-v3-migration-tests

mxyng/fix-create

jmorganca/cloud-errors

pdevine/parser-tidy

revert-12233-parth/simplify-entrypoints-runner

parth/enable-so-gpt-oss

brucemacd/qwen3vl

jmorganca/readme-simplify

parth/gpt-oss-structured-outputs

revert-12039-jmorganca/tools-braces

mxyng/embeddings

mxyng/gguf

mxyng/benchmark

mxyng/types-null

parth/move-parsing

mxyng/gemma2

jmorganca/docs

mxyng/16-bit

mxyng/create-stdin

pdevine/authorizedkeys

mxyng/quant

parth/opt-in-error-context-window

brucemacd/cache-models

brucemacd/runner-completion

jmorganca/llama-update-6

brucemacd/benchmark-list

brucemacd/partial-read-caps

parth/deepseek-r1-tools

mxyng/omit-array

parth/tool-prefix-temp

brucemacd/runner-test

jmorganca/qwen25vl

brucemacd/model-forward-test-ext

parth/python-function-parsing

jmorganca/cuda-compression-none

drifkin/num-parallel

drifkin/chat-truncation-fix

jmorganca/sync

parth/python-tools-calling

drifkin/array-head-count

brucemacd/create-no-loop

parth/server-enable-content-stream-with-tools

qwen25omni

mxyng/v3

brucemacd/ropeconfig

jmorganca/silence-tokenizer

parth/sample-so-test

parth/sampling-structured-outputs

brucemacd/doc-go-engine

parth/constrained-sampling-json

jmorganca/mistral-wip

brucemacd/mistral-small-convert

parth/sample-unmarshal-json-for-params

brucemacd/jomorganca/mistral

pdevine/bfloat16

jmorganca/mistral

brucemacd/mistral

pdevine/logging

parth/sample-correctness-fix

parth/sample-fix-sorting

jmorgan/sample-fix-sorting-extras

jmorganca/temp-0-images

brucemacd/parallel-embed-models

brucemacd/shim-grammar

jmorganca/fix-gguf-error

bmizerany/nameswork

jmorganca/faster-releases

bmizerany/validatenames

brucemacd/err-no-vocab

brucemacd/rope-config

brucemacd/err-hint

brucemacd/qwen2_5

brucemacd/logprobs

brucemacd/new_runner_graph_bench

progress-flicker

brucemacd/forward-test

brucemacd/go_qwen2

pdevine/gemma2

jmorganca/add-missing-symlink-eval

mxyng/next-debug

parth/set-context-size-openai

brucemacd/next-bpe-bench

brucemacd/next-bpe-test

brucemacd/new_runner_e2e

brucemacd/new_runner_qwen2

pdevine/convert-cohere2

brucemacd/convert-cli

parth/log-probs

mxyng/next-mlx

mxyng/cmd-history

parth/templating

parth/tokenize-detokenize

brucemacd/check-key-register

bmizerany/grammar

jmorganca/vendor-081b29bd

mxyng/func-checks

jmorganca/fix-null-format

parth/fix-default-to-warn-json

jmorganca/qwen2vl

jmorganca/no-concat

parth/cmd-cleanup-SO

brucemacd/check-key-register-structured-err

parth/openai-stream-usage

parth/fix-referencing-so

stream-tools-stop

jmorganca/degin-1

brucemacd/install-path-clean

brucemacd/push-name-validation

brucemacd/browser-key-register

jmorganca/openai-fix-first-message

jmorganca/fix-proxy

jessegross/sample

parth/disallow-streaming-tools

dhiltgen/remove_submodule

jmorganca/ga

jmorganca/mllama

pdevine/newlines

pdevine/geems-2b

jmorganca/llama-bump

mxyng/modelname-7

mxyng/gin-slog

mxyng/modelname-6

jyan/convert-prog

jyan/quant5

paligemma-support

pdevine/import-docs

jmorganca/openai-context

jyan/paligemma

jyan/p2

jyan/palitest

bmizerany/embedspeedup

jmorganca/llama-vit

brucemacd/allow-ollama

royh/ep-methods

royh/whisper

mxyng/api-models

mxyng/fix-memory

jyan/q4_4/8

jyan/ollama-v

royh/stream-tools

roy-embed-parallel

bmizerany/hrm

revert-5963-revert-5924-mxyng/llama3.1-rope

royh/embed-viz

jyan/local2

jyan/auth

jyan/local

jyan/parse-temp

jmorganca/template-mistral

jyan/reord-g

royh-openai-suffixdocs

royh-imgembed

royh-embed-parallel

jyan/quant4

royh-precision

jyan/progress

pdevine/fix-template

jyan/quant3

pdevine/ggla

mxyng/update-registry-domain

jmorganca/ggml-static

mxyng/create-context

jyan/v0.146

mxyng/layers-from-files

build_dist

bmizerany/noseek

royh-ls

royh-name

timeout

mxyng/server-timestamp

bmizerany/nosillyggufslurps

royh-params

jmorganca/llama-cpp-7c26775

royh-openai-delete

royh-show-rigid

jmorganca/enable-fa

jmorganca/no-error-template

jyan/format

royh-testdelete

bmizerany/fastverify

language_support

pdevine/ps-glitches

brucemacd/tokenize

bruce/iq-quants

bmizerany/filepathwithcoloninhost

mxyng/split-bin

bmizerany/client-registry

jmorganca/if-none-match

native

jmorganca/native

jmorganca/batch-embeddings

jmorganca/initcmake

jmorganca/mm

pdevine/showggmlinfo

modenameenforcealphanum

bmizerany/modenameenforcealphanum

jmorganca/done-reason

jmorganca/llama-cpp-8960fe8

ollama.com

bmizerany/filepathnobuild

bmizerany/types/model/defaultfix

rmdisplaylong

nogogen

bmizerany/x

modelfile-readme

bmizerany/replacecolon

jmorganca/limit

jmorganca/execstack

jmorganca/replace-assets

mxyng/tune-concurrency

jmorganca/testing

whitespace-detection

jmorganca/options

upgrade-all

scratch

cuda-search

mattw/airenamer

mattw/allmodelsonhuggingface

mattw/quantcontext

mattw/whatneedstorun

brucemacd/llama-mem-calc

mattw/faq-context

mattw/communitylinks

mattw/noprune

mattw/python-functioncalling

rename

mxyng/install

pulse

remove-first

editor

mattw/selfqueryingretrieval

cgo

mattw/howtoquant

api

matt/streamingapi

format-config

mxyng/extra-args

shell

update-nous-hermes

cp-model

upload-progress

fix-unknown-model

fix-model-names

delete-fix

insecure-registry

ls

deletemodels

progressbar

readme-updates

license-layers

skip-list

list-models

modelpath

matt/examplemodelfiles

distribution

go-opts

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/ollama#7229