The freedom AI stack.

localhost
Based in Canada
Open WebUIにLM StudioとComfyUIを連携させて結構良い所まで行けた!
1
1
23
6,465
The stars have aligned, v0.6.16 is conjured!✨
3
7
72
9,661
Now you can directly record your voice, capture audio from meetings like Google Meet or Zoom (browser only, dedicated apps may have limitations), or upload an audio file—get the transcription and enhance your notes.
1
4
42
5,856
zoom in. stop. ENHANCE. with the right combination of algorithms...we can read the meaning between the lines. introducing: notes
7
4
96
13,550
🔨
6
13
234
17,820
Replying to @stevewdavens
@Namecheap blocked us for no reason, investigating atm.
2
110
Analyzing...
16
28
487
44,825
🚀 You can now run 1.58-bit DeepSeek-R1 (non-distilled version) on Open WebUI with llama.cpp, thanks to @UnslothAI! 💻⚡️ (Tested on M4 Max, 128GB RAM) 📝 Dive into the details in their blog post: unsloth.ai/blog/deepseekr1-d…👈✨
Introducing 1.58bit DeepSeek-R1 GGUFs! 🐋 DeepSeek-R1 can now run in 1.58-bit, while being fully functional. We shrank the 671B parameter model from 720GB to just 131GB - a 80% size reduction. Naively quantizing all layers breaks the model entirely, causing endless loops & gibberish outputs. Our dynamic quants solve this. The 1.58-bit quant fits in 160GB VRAM (2x H100 80GB) for fast inference at ~140 tokens/sec. By studying DeepSeek-R1’s architecture, we selectively quantized certain layers to higher bits (like 4-bit), and leave most MoE layers to 1.5-bit. Benchmarks + Blog: unsloth.ai/blog/deepseekr1-d… Dynamic GGUFs (131GB–212GB) on Hugging Face: huggingface.co/unsloth/DeepS…
4
43
246
34,017
👀
10
5
79
5,685
Installing...
32
54
1,314
183,745
Life could be a dream
11
8
192
69,097
Open WebUI Math Bot ➕🤖 by @pad4651
Replying to @sergedoub
Yes! Exactly. Bot-to-Bot interactions are absolutely part of the vision. We’ll provide boilerplate bot examples for all permutations (Bot ↔️ Bot, Bot ↔️ Human, Human ↔️ Human) to make building in every context easier. Check out: github.com/open-webui/bot
1
36
6,397
OpenWebUI 0.4.7 is here, and with it, message auto-completion. Start typing, and let us finish your thoughts—seamlessly, intuitively. Sometimes, all you needed was that one missing piece.✨ github.com/open-webui/open-w…
5
10
98
6,103
Yes! Supported by default, all thanks to Ollama and their amazing team 🙌
1
22
550
What if we told you... 😎
1
2
224
Replying to @TomDavenport
If OpenAI models are all you need, you can just add your api keys from Settings > Connections!
2
1
95
4
623