Jan
@jandotai.bsky.social
Open source ChatGPT-alternative that runs 100% offline.
Introducing Jan-v2-VL, a multimodal agent built for long-horizon tasks.
Jan-v2-VL executes 49 steps without failure, while the base model stops at 5 and other similar-scale VLMs stop between 1 and 2.
Models: huggingface.co/collections...
Credit to the Qwen team for Qwen3-VL-8B-Thinking!
Jan-v2-VL executes 49 steps without failure, while the base model stops at 5 and other similar-scale VLMs stop between 1 and 2.
Models: huggingface.co/collections...
Credit to the Qwen team for Qwen3-VL-8B-Thinking!
November 13, 2025 at 10:29 AM
Introducing Jan-v2-VL, a multimodal agent built for long-horizon tasks.
Jan-v2-VL executes 49 steps without failure, while the base model stops at 5 and other similar-scale VLMs stop between 1 and 2.
Models: huggingface.co/collections...
Credit to the Qwen team for Qwen3-VL-8B-Thinking!
Jan-v2-VL executes 49 steps without failure, while the base model stops at 5 and other similar-scale VLMs stop between 1 and 2.
Models: huggingface.co/collections...
Credit to the Qwen team for Qwen3-VL-8B-Thinking!
You can run Kimi-K2-Thinking, the most strongest agentic model, in Jan through Hugging Face. Add it to your Hugging Face Inference models to use it.
November 7, 2025 at 6:50 AM
You can run Kimi-K2-Thinking, the most strongest agentic model, in Jan through Hugging Face. Add it to your Hugging Face Inference models to use it.
What's the highest number of tools your models could use in Jan?
November 4, 2025 at 3:45 AM
What's the highest number of tools your models could use in Jan?
You can now use Qwen3-VL in Jan.
Find the GGUF model on Hugging Face, click "Use this model" and select Jan, or copy the model link and paste it into Jan Hub.
Thanks Qwen 🧡
Find the GGUF model on Hugging Face, click "Use this model" and select Jan, or copy the model link and paste it into Jan Hub.
Thanks Qwen 🧡
November 3, 2025 at 10:28 AM
You can now use Qwen3-VL in Jan.
Find the GGUF model on Hugging Face, click "Use this model" and select Jan, or copy the model link and paste it into Jan Hub.
Thanks Qwen 🧡
Find the GGUF model on Hugging Face, click "Use this model" and select Jan, or copy the model link and paste it into Jan Hub.
Thanks Qwen 🧡
llama.cpp in Jan has been updated. Tap "Update Now", or update it from Settings. Thanks to GGML and the open-source community 💙
November 3, 2025 at 8:13 AM
llama.cpp in Jan has been updated. Tap "Update Now", or update it from Settings. Thanks to GGML and the open-source community 💙
ANNOUNCEMENT | We've seen multiple tokens appearing under the name "Jan," some using our branding and visuals without authorization. These projects have no link to us. Please be cautious and trust only our official accounts for verified information.
October 31, 2025 at 3:39 AM
ANNOUNCEMENT | We've seen multiple tokens appearing under the name "Jan," some using our branding and visuals without authorization. These projects have no link to us. Please be cautious and trust only our official accounts for verified information.
Run gpt-oss-safeguard-20b in Jan via Groq with 1k+ tokens/sec ⚡️
October 29, 2025 at 12:42 PM
Run gpt-oss-safeguard-20b in Jan via Groq with 1k+ tokens/sec ⚡️
Your Ollama models can use MCP servers in Jan.
October 29, 2025 at 8:01 AM
Your Ollama models can use MCP servers in Jan.
You can now run Ollama models in Jan.
Go to Settings, Model Providers, add Ollama, and set the Base URL to http://localhost:11434/v1.
Your 🦙 Ollama models will then be ready to use in 👋 Jan.
Go to Settings, Model Providers, add Ollama, and set the Base URL to http://localhost:11434/v1.
Your 🦙 Ollama models will then be ready to use in 👋 Jan.
October 29, 2025 at 6:25 AM
You can now run Ollama models in Jan.
Go to Settings, Model Providers, add Ollama, and set the Base URL to http://localhost:11434/v1.
Your 🦙 Ollama models will then be ready to use in 👋 Jan.
Go to Settings, Model Providers, add Ollama, and set the Base URL to http://localhost:11434/v1.
Your 🦙 Ollama models will then be ready to use in 👋 Jan.
Jan can now search the web using Exa. Turn it on from the MCP section.
October 28, 2025 at 10:18 AM
Jan can now search the web using Exa. Turn it on from the MCP section.
Jan now shows how much of the context window your chat uses.
October 28, 2025 at 1:33 AM
Jan now shows how much of the context window your chat uses.
Kimi K2 runs in Jan.
Find it in Jan Hub, download, and you're good to go.
Find it in Jan Hub, download, and you're good to go.
October 20, 2025 at 5:48 AM
Kimi K2 runs in Jan.
Find it in Jan Hub, download, and you're good to go.
Find it in Jan Hub, download, and you're good to go.
Organize chats with Projects in Jan v0.7.0.
This update brings:
- Projects to group related chats
- Model context stats
- Auto-loaded cloud models
- Support for Exa as an MCP Server
Update your Jan or download the latest version.
This update brings:
- Projects to group related chats
- Model context stats
- Auto-loaded cloud models
- Support for Exa as an MCP Server
Update your Jan or download the latest version.
October 2, 2025 at 9:45 AM
Organize chats with Projects in Jan v0.7.0.
This update brings:
- Projects to group related chats
- Model context stats
- Auto-loaded cloud models
- Support for Exa as an MCP Server
Update your Jan or download the latest version.
This update brings:
- Projects to group related chats
- Model context stats
- Auto-loaded cloud models
- Support for Exa as an MCP Server
Update your Jan or download the latest version.
You can run GGUF models from Hugging Face in Jan.
Jan Hub searches @huggingface and runs them with @ggml's llama.cpp 💙
Jan Hub searches @huggingface and runs them with @ggml's llama.cpp 💙
October 2, 2025 at 6:21 AM
You can run GGUF models from Hugging Face in Jan.
Jan Hub searches @huggingface and runs them with @ggml's llama.cpp 💙
Jan Hub searches @huggingface and runs them with @ggml's llama.cpp 💙
You can adjust model settings yourself or let Jan optimize them for your device.
September 30, 2025 at 4:23 AM
You can adjust model settings yourself or let Jan optimize them for your device.
You can now auto-adjust llama.cpp settings. It's an experimental feature to help your models run more efficiently.
September 19, 2025 at 5:11 AM
You can now auto-adjust llama.cpp settings. It's an experimental feature to help your models run more efficiently.
Jan v0.6.10 is out: You can now import vision models too.
- Import your vision models
- Experimental setting auto-adjusts llama.cpp for your system
- Fixed: image attachments, copy glitches, API key visibility, and more
Update your Jan or download the latest.
- Import your vision models
- Experimental setting auto-adjusts llama.cpp for your system
- Fixed: image attachments, copy glitches, API key visibility, and more
Update your Jan or download the latest.
September 18, 2025 at 9:18 AM
Jan v0.6.10 is out: You can now import vision models too.
- Import your vision models
- Experimental setting auto-adjusts llama.cpp for your system
- Fixed: image attachments, copy glitches, API key visibility, and more
Update your Jan or download the latest.
- Import your vision models
- Experimental setting auto-adjusts llama.cpp for your system
- Fixed: image attachments, copy glitches, API key visibility, and more
Update your Jan or download the latest.
Jan is lighter than ever.
September 17, 2025 at 9:06 AM
Jan is lighter than ever.
Some conversations are too private for cloud AI.
Create your own assistant in 👋 Jan, make it a lawyer, finance, or customer support.
Choose an open-source model and keep every word private.
Create your own assistant in 👋 Jan, make it a lawyer, finance, or customer support.
Choose an open-source model and keep every word private.
September 17, 2025 at 8:08 AM
Some conversations are too private for cloud AI.
Create your own assistant in 👋 Jan, make it a lawyer, finance, or customer support.
Choose an open-source model and keep every word private.
Create your own assistant in 👋 Jan, make it a lawyer, finance, or customer support.
Choose an open-source model and keep every word private.
Jan v1 is now more reliable when handling searches.
Performance:
- Gains on reasoning & creativity benchmarks
- Small drop on SimpleQA (91.1 -> 90.7)
Model:
- huggingface.co/janhq/Jan-v...
- GGUF: huggingface.co/janhq/Jan-v...
Credit to the Qwen team for Qwen3-4B-Thinking and GGML for llama.cpp.
Performance:
- Gains on reasoning & creativity benchmarks
- Small drop on SimpleQA (91.1 -> 90.7)
Model:
- huggingface.co/janhq/Jan-v...
- GGUF: huggingface.co/janhq/Jan-v...
Credit to the Qwen team for Qwen3-4B-Thinking and GGML for llama.cpp.
September 9, 2025 at 7:34 AM
Jan v1 is now more reliable when handling searches.
Performance:
- Gains on reasoning & creativity benchmarks
- Small drop on SimpleQA (91.1 -> 90.7)
Model:
- huggingface.co/janhq/Jan-v...
- GGUF: huggingface.co/janhq/Jan-v...
Credit to the Qwen team for Qwen3-4B-Thinking and GGML for llama.cpp.
Performance:
- Gains on reasoning & creativity benchmarks
- Small drop on SimpleQA (91.1 -> 90.7)
Model:
- huggingface.co/janhq/Jan-v...
- GGUF: huggingface.co/janhq/Jan-v...
Credit to the Qwen team for Qwen3-4B-Thinking and GGML for llama.cpp.
Jan now runs faster on CUDA.
We updated llama.cpp with the latest improvements and fixed a CUDA backend bug upstream. Jan stays pinned to v6324 due to flash-attention changes.
If you have auto-update on, you'll get this automatically - if not, we recommend turning it on.
We updated llama.cpp with the latest improvements and fixed a CUDA backend bug upstream. Jan stays pinned to v6324 due to flash-attention changes.
If you have auto-update on, you'll get this automatically - if not, we recommend turning it on.
September 8, 2025 at 8:48 AM
Jan now runs faster on CUDA.
We updated llama.cpp with the latest improvements and fixed a CUDA backend bug upstream. Jan stays pinned to v6324 due to flash-attention changes.
If you have auto-update on, you'll get this automatically - if not, we recommend turning it on.
We updated llama.cpp with the latest improvements and fixed a CUDA backend bug upstream. Jan stays pinned to v6324 due to flash-attention changes.
If you have auto-update on, you'll get this automatically - if not, we recommend turning it on.
You can now connect MCP servers to Jan via HTTP & SSE, as well as STDIO.
September 5, 2025 at 2:16 AM
You can now connect MCP servers to Jan via HTTP & SSE, as well as STDIO.
Meet Jan-v1-edge: an experimental 1.7B distilled model for Perplexity-style search.
We're testing how well web search & reasoning can transfer into a smaller 1.7B model.
- Jan-v1-edge: huggingface.co/janhq/Jan-v...
- Jan-v1-edge GGUF: huggingface.co/janhq/Jan-v...
We're testing how well web search & reasoning can transfer into a smaller 1.7B model.
- Jan-v1-edge: huggingface.co/janhq/Jan-v...
- Jan-v1-edge GGUF: huggingface.co/janhq/Jan-v...
September 4, 2025 at 8:19 AM
Meet Jan-v1-edge: an experimental 1.7B distilled model for Perplexity-style search.
We're testing how well web search & reasoning can transfer into a smaller 1.7B model.
- Jan-v1-edge: huggingface.co/janhq/Jan-v...
- Jan-v1-edge GGUF: huggingface.co/janhq/Jan-v...
We're testing how well web search & reasoning can transfer into a smaller 1.7B model.
- Jan-v1-edge: huggingface.co/janhq/Jan-v...
- Jan-v1-edge GGUF: huggingface.co/janhq/Jan-v...
AI is the most personal tech we've ever built. It shouldn't be watched. Jan keeps it yours, private, open-source, easy to use.
September 4, 2025 at 3:38 AM
AI is the most personal tech we've ever built. It shouldn't be watched. Jan keeps it yours, private, open-source, easy to use.