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 #10893] DeepSeek-R1-0528 Model Request #7160

New Issue
Closed
opened 2026-04-12 19:09:37 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-12 19:09:37 -05:00
Owner
Copy Link

Originally created by @weiquanju on GitHub (May 29, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10893

DeepSeek-R1-0528 今天已经发布了，什么时候可以上ollama

DeepSeek-R1-0528 has been released today, when can it be uploaded to ollama

Originally created by @weiquanju on GitHub (May 29, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10893 [DeepSeek-R1-0528](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528) 今天已经发布了，什么时候可以上ollama [DeepSeek-R1-0528](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528) has been released today, when can it be uploaded to ollama
GiteaMirror added the model label 2026-04-12 19:09:37 -05:00
GiteaMirror commented 2026-04-12 19:09:38 -05:00
Author
Owner
Copy Link

@mu-dan commented on GitHub (May 29, 2025):

DeepSeek-R1-0528 今天已经发布了，什么时候可以上ollama

DeepSeek-R1-0528 今日已发布，什么时候可以上传到 ollama

It seems that this version is 685b parameters, and there is no distillation model, really, can the computing resources withstand the landlord
好像这个版本是685b参数,而且没有蒸馏模型,真上了,算力资源能顶得住了吗楼主[Doge]

<!-- gh-comment-id:2918560805 --> @mu-dan commented on GitHub (May 29, 2025): > [DeepSeek-R1-0528](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528) 今天已经发布了，什么时候可以上ollama > > [DeepSeek-R1-0528](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528) 今日已发布，什么时候可以上传到 ollama It seems that this version is 685b parameters, and there is no distillation model, really, can the computing resources withstand the landlord 好像这个版本是685b参数,而且没有蒸馏模型,真上了,算力资源能顶得住了吗楼主[Doge]
GiteaMirror commented 2026-04-12 19:09:38 -05:00
Author
Owner
Copy Link

@olumolu commented on GitHub (May 29, 2025):

support also v3.1 https://huggingface.co/deepseek-ai/DeepSeek-V3-0324

<!-- gh-comment-id:2918587945 --> @olumolu commented on GitHub (May 29, 2025): support also v3.1 https://huggingface.co/deepseek-ai/DeepSeek-V3-0324
GiteaMirror commented 2026-04-12 19:09:39 -05:00
Author
Owner
Copy Link

@a1ix2 commented on GitHub (May 30, 2025):

There is an 8B distilled version based on Qwen3
https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
but when trying to import it from the huggingface safetensors in ollama v0.9.0 I get the following error

~$ ollama create deepseek-r1:8b-0528-qwen3-fp16 -f deepseek-r1-0528-qwen3-8b.Modelfile 
gathering model components 
copying file sha256:7bb656406ecf282bcb44b87a93c0daa2c0ef32d1b335fdef65722e8c45d28fe3 100% 
copying file sha256:1b1cbbba841c180e94192f7a25d2d97e21498fc1a0a0b4785942158af5eee183 100% 
copying file sha256:8c3631d826c04565ad79c026fa291cd142aa4b75c69cc717f9c513e2ed061b4e 100% 
copying file sha256:47d3a3ffb1ff38eb6a22f8a2d207306bfa3ea2499ff70df4baeaa559bf7453c7 100% 
copying file sha256:a1719a4728ba274510dcae1d04474bd8a1e55270b8e756b750f92accf47e7557 100% 
copying file sha256:78872f2c1f0a5fb79d5872dbacb4c83991ef416315a25f34659e6a7c34108027 100% 
converting model 
Error: unsupported architecture "Qwen3ForCausalLM"
<!-- gh-comment-id:2922824426 --> @a1ix2 commented on GitHub (May 30, 2025): There is an 8B distilled version based on Qwen3 https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B but when trying to import it from the huggingface safetensors in ollama v0.9.0 I get the following error ``` ~$ ollama create deepseek-r1:8b-0528-qwen3-fp16 -f deepseek-r1-0528-qwen3-8b.Modelfile gathering model components copying file sha256:7bb656406ecf282bcb44b87a93c0daa2c0ef32d1b335fdef65722e8c45d28fe3 100% copying file sha256:1b1cbbba841c180e94192f7a25d2d97e21498fc1a0a0b4785942158af5eee183 100% copying file sha256:8c3631d826c04565ad79c026fa291cd142aa4b75c69cc717f9c513e2ed061b4e 100% copying file sha256:47d3a3ffb1ff38eb6a22f8a2d207306bfa3ea2499ff70df4baeaa559bf7453c7 100% copying file sha256:a1719a4728ba274510dcae1d04474bd8a1e55270b8e756b750f92accf47e7557 100% copying file sha256:78872f2c1f0a5fb79d5872dbacb4c83991ef416315a25f34659e6a7c34108027 100% converting model Error: unsupported architecture "Qwen3ForCausalLM" ```
GiteaMirror commented 2026-04-12 19:09:39 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jun 2, 2025):

https://ollama.com/library/deepseek-r1:671b-0528-q4_K_M

<!-- gh-comment-id:2929332630 --> @rick-github commented on GitHub (Jun 2, 2025): https://ollama.com/library/deepseek-r1:671b-0528-q4_K_M
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#7160
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?