ollama ollama issues - Githubissues

ollama / ollama

Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, and other large language models.

https://ollama.com

MIT License

134.99k stars 11.2k forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

404 Page Not Found when trying to access /api/generate

#10016 Sunny-DCosta opened 1 minute ago
0
Final stream chunk missing "done": true despite completed response

#10015 jopersr opened 1 hour ago
1
Podman on Ubuntu can't find gpus

#10014 thezachdrake opened 2 hours ago
4
Show GPU system requirements for each model

#10013 RustoMCSpit closed 32 minutes ago
1
num_ctx

#10012 20246688 opened 6 hours ago
3
OLLAMA_NUM_PARALLEL not working

#10011 forReason opened 6 hours ago
4
Error: could not connect to ollama app, is it running?

#10010 hao45e closed 9 hours ago
2
Question: Changelog of updated models

#10009 zivanfi closed 4 hours ago
2
Request for Help: Checking My ollama - Python - Based Embed Code

#10008 20246688 opened 12 hours ago
3
ollama uses multiple GPU resources

#10007 cigar-wiki opened 13 hours ago
1
docs: make context length faq readable

#10006 ParthSareen closed 16 hours ago
0
runner: Release semaphore and improve error messages on failures

#10005 jessegross opened 17 hours ago
0
Add full support for omni models

#10004 flexiworld opened 17 hours ago
0
server: prevent model thrashing from unset API fields

#10003 rick-github opened 23 hours ago
0
add qwen 2.5 VL 32B model

#10002 olumolu closed 23 hours ago
0
Improve compatibility with OpenAI structured outputs json_schema response format

#10001 SuperPat45 closed 3 hours ago
2
How do I make a model simply complete my text?

#10000 Explosion-Scratch closed 34 minutes ago
6
[ENHANCE] Add Ubuntu Support for AMD Ryzen AI 9 HX 370 w/ Radeon 890M (gfx1150)

#9999 liuchuan01 opened 1 day ago
0
Segmentation fault

#9998 Hml520QQ opened 1 day ago
2
Qwen2.5-VL-32B

#9997 enryteam closed 1 day ago
0
plz add : `ollama stop all`

#9996 NGC13009 opened 1 day ago
0
Ollama runs a multimodal model

#9995 Gusha-nye closed 1 day ago
2
ollama cannot running until restrat it

#9994 Liuyuan0803 opened 1 day ago
5
不能聊天

#9993 bmb-li closed 1 day ago
2
Qwen2.5-vl-32B wanted!!

#9992 twythebest closed 1 day ago
0
server: Improve download reliability in bandwidth-constrained environments.

#9991 monolith-jaehoon opened 1 day ago
0
Inaccurate model size display in ollama ps command

#9990 jaybom opened 1 day ago
4
how to accelerate the inference speed of the model

#9989 Tu1231 closed 8 hours ago
2
Incorrect memory requirement calculation for small models (32B model showing 659.2 GiB requirement)

#9988 jaybom opened 1 day ago
4
Improve memory estimates for sliding window attention

#9987 jessegross closed 20 hours ago
0
ollama runners crashing with wsarecv: An existing connection was forcibly closed by the remote host

#9986 azizbtk opened 1 day ago
1
Discrepancy Between API Documentation and Actual Response: name vs model Field

#9985 CristianoMafraJunior closed 16 hours ago
2
Add support for array for head count GGUF KV

#9984 ngxson opened 2 days ago
1
Update README.md

#9983 uggrock opened 2 days ago
0
do we have official ollama docker image < 1 GB

#9982 babu-kandyala opened 2 days ago
8
Hope to support the Qwen2.5-VL-32B-Instruct

#9981 Czj1997-02 closed 2 days ago
0
Update DeepSeek V3 to improved version

#9980 bannert1337 opened 2 days ago
2
Vision models: regex sometimes doesn't catch file name from prompt

#9979 RicoElectrico opened 2 days ago
1
config: allow setting fixed context length

#9978 pppy2012 opened 2 days ago
0
How can we prevent creating a new complete model instance in GPU when using different context lengths?

#9977 jaybom opened 2 days ago
1
segmentation violation GGML_ASSERT(sections.v[0] > 0 || sections.v[1] > 0 || sections.v[2] > 0)

#9976 thafer6 opened 2 days ago
1
dify中不同的模型启动模型上下文长度参数会导致启动不同的模型实例到显存中吗

#9975 jaybom opened 2 days ago
2
运行模型时，gpu利用率占满，但是功率很低，gpu没有正常使用起来

#9974 save-FGG opened 2 days ago
3
server: support streaming near tool usage

#9973 fizx opened 2 days ago
5
wsarecv: An existing connection was forcibly closed by the remote host.

#9972 upendravalera opened 2 days ago
4
Please support Qwen 2.5 VL 32B

#9971 Jigit-ship-it closed 2 days ago
0
RX6600 detected but not used (Linux)

#9970 LevitatingBusinessMan closed 2 days ago
1
Some Questions about Using Embedding Models in Ollama

#9969 20246688 closed 1 day ago
2
llama runner process has terminated: exit status 2

#9968 Andyshenjx opened 2 days ago
1
Ollama model files for Gemma3 specifying mmproj ggufs do not retain vision capability.

#9967 lkraven closed 2 days ago
4