ollama / ollama

Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.

https://ollama.com

ollama/ollama Issues

support for arm linux
Closed 16 days ago4
Error: llama runner process has terminated: exit status 0xc0000409 error loading model: unable to allocate backend buffer
Closed 16 days ago9
service hang after some requests to /api/embeddings
Updated a month ago2
support minicpm language model
Updated a month ago1
bug: Open WebUI RAG Malfunction with Ollama Versions Post 0.2.1
Closed a month ago15
error loading model: unable to allocate backend buffer when model size is > VRAM with multiple GPUs
Updated a month ago2
ollama save model to file and ollama load model from file
Closed a month ago1
ollama 0.2.7 function call error "llama3 does not support tools"
Closed a month ago7
New Command/ Flag to notify or download latest updates to an already pulled model.
Updated a month ago3
specify a single GPU （id=1）using Docker, Error!
Closed a month ago2
Request to add support for InternVL-2 model
Updated a month ago2
last chunk does not return tools and "finished_reason": "tools_calls"
Updated a month ago15
how to run in only GPU mode
Closed a month ago6
How can I make the model produce consistent and stable results for the same prompt?
Updated a month ago1
Can we add the new smollm models
Closed a month ago4
OLLAMA_MAX_VRAM is ignored
Closed a month ago2
Mistral Nemo Please!
Closed a month ago28
Upgraded hardware no change in performance
Closed a month ago2
Ollama seems to be limited by single CPU thread on multi GPU machine with parallel processing enable
Closed a month ago3
Ollama v0.2.+ with phi3:mini increased RAM consumption compared to 0.1.48
Closed a month ago5
Docker image has Critical CVE-2024-24790 due to Go version 1.22.1
Closed a month ago
erorr loading models x3 7900 XTX #5708
Closed a month ago1
please add `https://huggingface.co/nvidia/Nemotron-4-340B-Instruct` to `https://ollama.com/library`
Updated a month ago2
ollama serve supports only llama3 for other models like gemma its 404 error
Updated a month ago14
ROCm Memory Issues with Long Contexts
Updated a month ago2
Tokenizer issue with tool calling with InternLM2
Closed a month ago5
Expose model capabilities via /api/tags and /v1/models[/model]
Updated a month ago1
Assistant doesn't continue from its last message
Closed a month ago4
allowing ollama 3 to access local txt files for a larger memory?
Updated a month ago2
ollama run deepseek-coder-v2 creates gibberish output
Updated a month ago7
unknown architecture DeepseekV2ForCausalLM
Closed a month ago1
Enable using llama.cpp's --model-draft <model> feature for speculative decoding
Updated a month ago1
Error 500 on `/api/embed`
Updated a month ago2
Ability to pass --predict to llama.cpp server in ollama
Updated a month ago1
Windows: could not connect to ollama app, is it running?
Closed a month ago6
add GraphRAG
Updated a month ago1
List command optional flag to display license
Updated a month ago
(linux) snap support for linux installation this will solve many issues
Updated a month ago
Support LoRA GGUF Adapters
Updated a month ago
How to Deploy LLM Based on ollama in an offline environment?
Closed a month ago13
process cant't kill on windows 10
Closed a month ago5
Search/Filter by license
Updated a month ago1
How to pass a custom file (txt\doc\pdf) to prompt through the API
Updated a month ago1
Favor idle GPUs that fit over largest free memory GPUs when scheduling
Updated a month ago
Update llama.cpp to support Ascend
Updated a month ago
Releases page: please also generate an archive with dependencies
Updated a month ago1
Support to Intel NPU by Intel NPU Acceleration Library
Updated a month ago
ShipIt folder taking 1GB
Updated a month ago
Model Cold Storage and user manual management possibility
Updated a month ago2
Endpoint for Listing models isn't working
Closed a month ago