Mixtral: Mixture of Experts

1. ollama-webui

   1 16 5,789 9.8 Svelte

   Discontinued ChatGPT-Style WebUI for LLMs (Formerly Ollama WebUI) [Moved to: https://github.com/open-webui/open-webui]

   

   On mac silicon:

   https://ollama.ai/

   ollama pull mixtral

   For a chatgpt-esk web ui

   https://github.com/ollama-webui/ollama-webui

   docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v ollama-webui:/app/backend/data --name ollama-webui --restart always ghcr.io/ollama-webui/ollama-webui:main

   Navigate to http://localhost:3000

   You can also use ollama in langchain.

2. InfluxDB

   influxdata.com featured

   InfluxDB high-performance time series database. Collect, organize, and act on massive volumes of high-resolution data to power real-time intelligent systems.

   

3. ollama

   2 461 138,252 9.9 Go

   Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.

   

   On mac silicon:

   https://ollama.ai/

   ollama pull mixtral

   For a chatgpt-esk web ui

   https://github.com/ollama-webui/ollama-webui

   docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v ollama-webui:/app/backend/data --name ollama-webui --restart always ghcr.io/ollama-webui/ollama-webui:main

   Navigate to http://localhost:3000

   You can also use ollama in langchain.

4. CogVLM

   3 16 6,487 8.9 Python

   a state-of-the-art-level open visual language model | 多模态预训练模型

   

   CogVLM is very good in my (brief) testing: https://github.com/THUDM/CogVLM

   The model weights seem to be under a non-commercial license, not true open source, but it is "open access" as you requested.

5. llamafile

   4 61 22,199 9.6 C++

   Distribute and run LLMs with a single file.

   

6. LLMstudio

   5 2 325 9.5 Python

   Framework to bring LLM applications to production

   

   Lmstudio (that they linked) is definitely not open source, and doesn't even offer a pricing model for business use.

   Llmstudio is, but I suspect that was a typo in their comment. https://github.com/TensorOpsAI/LLMStudio

7. llama.cpp

   6 882 78,399 10.0 C++

   LLM inference in C/C++

   

   > The output quality is not "ruined" at all.

   That was my experience as well.

   I also tried 2-bit version, and it was horrible.

   However, there is a new approach in the works[1] (merged yesterday) which works surprisingly well with 2.10 bits per weight (12.3 GB model size)

   [1] https://github.com/ggerganov/llama.cpp/pull/4773

Suggest a related project