Loading video...

Video Failed to Load

Go Home

Introducing Jan-Code-4B ๐Ÿ’ป A compact coding model tuned for practical day-to-day tasks. Generation, refactors, debugging, tests โ€” all runnable locally in Jan. Download Jan: Model:

jandotai's profile picture

๐Ÿ‘‹ Jan

13,110 subscribers

109,873 views โ€ข 3 months ago โ€ขvia X (Twitter)

LIVE

Anya Rossiโ€ข Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Introducing Jan-v1: 4B model for web search, an open-source alternative to Perplexity Pro. In our evals, Jan v1 delivers 91% SimpleQA accuracy, slightly outperforming Perplexity Pro while running fully locally. Use cases: - Web search - Deep Research Built on the new version of Qwen's Qwen3-4B-Thinking (up to 256k context length), fine-tuned for reasoning and tool use in Jan. You can run the model in Jan, llama.cpp, or vLLM. To enable search in Jan, go to Settings โ†’ Experimental Features โ†’ On, then Settings โ†’ MCP Servers โ†’ enable a search-related MCP such as Serper. Use the model: - Jan-v1-4B: - Jan-v1-4B-GGUF: Credit to the Qwen team for Qwen3 4B Thinking & Georgi Gerganov for llama.cpp.
0:24

Introducing Jan-v1: 4B model for web search, an open-source alternative to Perplexity Pro. In our evals, Jan v1 delivers 91% SimpleQA accuracy, slightly outperforming Perplexity Pro while running fully locally. Use cases: - Web search - Deep Research Built on the new version of Qwen's Qwen3-4B-Thinking (up to 256k context length), fine-tuned for reasoning and tool use in Jan. You can run the model in Jan, llama.cpp, or vLLM. To enable search in Jan, go to Settings โ†’ Experimental Features โ†’ On, then Settings โ†’ MCP Servers โ†’ enable a search-related MCP such as Serper. Use the model: - Jan-v1-4B: - Jan-v1-4B-GGUF: Credit to the Qwen team for Qwen3 4B Thinking & Georgi Gerganov for llama.cpp.

๐Ÿ‘‹ Jan

689,722 views โ€ข 9 months ago

Meet Jan-nano, a 4B model that outscores DeepSeek-v3-671B using MCP. It's built on Qwen3-4B with DAPO fine-tuning, it handles: - real-time web search - deep research Model + GGUF: To run it locally: - Install Jan Beta: - Download Jan-nano in Jan Hub - Settings -> MCP, enable MCP and add your Serper API key for web tools Full technical report will be published shortly.
0:55

Meet Jan-nano, a 4B model that outscores DeepSeek-v3-671B using MCP. It's built on Qwen3-4B with DAPO fine-tuning, it handles: - real-time web search - deep research Model + GGUF: To run it locally: - Install Jan Beta: - Download Jan-nano in Jan Hub - Settings -> MCP, enable MCP and add your Serper API key for web tools Full technical report will be published shortly.

Menlo Research

56,109 views โ€ข 11 months ago

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. It achieves longer, stable task execution in your browser without accuracy loss. 3 variants are available: - Jan-v2-VL-low (efficiency-oriented) - Jan-v2-VL-med (balanced) - Jan-v2-VL-high (deeper reasoning and longer execution) Models: To use it, update your Jan App and download Jan-v2-VL from the Model Hub. Activate Browser MCP servers for agentic use cases. Credit to the Qwen team for Qwen3-VL-8B-Thinking base model.
0:52

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. It achieves longer, stable task execution in your browser without accuracy loss. 3 variants are available: - Jan-v2-VL-low (efficiency-oriented) - Jan-v2-VL-med (balanced) - Jan-v2-VL-high (deeper reasoning and longer execution) Models: To use it, update your Jan App and download Jan-v2-VL from the Model Hub. Activate Browser MCP servers for agentic use cases. Credit to the Qwen team for Qwen3-VL-8B-Thinking base model.

๐Ÿ‘‹ Jan

129,906 views โ€ข 6 months ago

Jan v1 is now more reliable when handling searches. It's an open-source alternative to Perplexity Pro, and it now avoids infinite loops with Jan v1 2509. Performance updates: - Gains on reasoning & creativity benchmarks - Small drop on SimpleQA (91.1 -> 90.7), still competitive with Perplexity Pro The updated version is live on Jan Hub. You can run the model in Jan, llama.cpp, or vLLM. Use the model: - Model: - GGUF: Shoutout to the Qwen team for Qwen3-4B Thinking and Georgi Gerganov for llama.cpp.
0:36

Jan v1 is now more reliable when handling searches. It's an open-source alternative to Perplexity Pro, and it now avoids infinite loops with Jan v1 2509. Performance updates: - Gains on reasoning & creativity benchmarks - Small drop on SimpleQA (91.1 -> 90.7), still competitive with Perplexity Pro The updated version is live on Jan Hub. You can run the model in Jan, llama.cpp, or vLLM. Use the model: - Model: - GGUF: Shoutout to the Qwen team for Qwen3-4B Thinking and Georgi Gerganov for llama.cpp.

๐Ÿ‘‹ Jan

17,759 views โ€ข 9 months ago

Introducing a brand new way to use Jan ๐Ÿ’› You can now search the web, do deep research, and let Jan use your browser. Powered by Jan-v2-VL-Max, 30B model beating Gemini 2.5 Pro & DeepSeek R1 on execution benchmarks. Try it:
3:05

Introducing a brand new way to use Jan ๐Ÿ’› You can now search the web, do deep research, and let Jan use your browser. Powered by Jan-v2-VL-Max, 30B model beating Gemini 2.5 Pro & DeepSeek R1 on execution benchmarks. Try it:

๐Ÿ‘‹ Jan

29,403 views โ€ข 5 months ago

SCHEDULE UPDATE: Jan 7th - No plans yet Jan 8th - A way out w/ A2Guapo Jan 9th - Off day Jan 10th - Vocal lessons w/ Bri Jan 11th - Matcha and making a song w/ Bri Jan 12th - Matcha related stream Jan 13th - Gym stream w/ LeanBeefPatty
0:42

SCHEDULE UPDATE: Jan 7th - No plans yet Jan 8th - A way out w/ A2Guapo Jan 9th - Off day Jan 10th - Vocal lessons w/ Bri Jan 11th - Matcha and making a song w/ Bri Jan 12th - Matcha related stream Jan 13th - Gym stream w/ LeanBeefPatty

Sakuzas

108,025 views โ€ข 5 months ago

Want to reduce your Claude Code bill? Claude Code uses smaller models like Haiku for simple tasks. Instead of sending every small request to a paid API, run those tasks locally with Jan and keep heavier work in the cloud. One setup. Lower API usage. More control. Get the latest version at
0:21

Want to reduce your Claude Code bill? Claude Code uses smaller models like Haiku for simple tasks. Instead of sending every small request to a paid API, run those tasks locally with Jan and keep heavier work in the cloud. One setup. Lower API usage. More control. Get the latest version at

๐Ÿ‘‹ Jan

13,085 views โ€ข 3 months ago

Thank you to everyone who has played The Alters and to 11 bit studios | NEW GAME REVEALED for letting me be part of The Alters | MAJOR UPDATE OUT NOW๐Ÿ‘ love from, Jan, Jan, Jan, Jan, Jan, Jan, Jan, Jan, Jan, Jan, and Jan. #TheAlters
0:51

Thank you to everyone who has played The Alters and to 11 bit studios | NEW GAME REVEALED for letting me be part of The Alters | MAJOR UPDATE OUT NOW๐Ÿ‘ love from, Jan, Jan, Jan, Jan, Jan, Jan, Jan, Jan, Jan, Jan, and Jan. #TheAlters

Alex Jordan

63,583 views โ€ข 11 months ago

This month on PlayStation ๐Ÿ“… ๐Ÿš€ Jan 15 - The Legend of Heroes: Trails Beyond the Horizon ๐Ÿ“ฑ Jan 16 - BrokenLore: Unfollow ๐Ÿ›ฐ๏ธ Jan 20 - MIO: Memories in Orbit ๐ŸŒ‘ Jan 22 - Arknights: Endfield ๐Ÿช“ Jan 29 - I Hate This Place ๐Ÿง—๐Ÿฝโ€โ™€๏ธ Jan 29 - Cairn ๐Ÿง› Jan 30 - Code Vein II
0:30

This month on PlayStation ๐Ÿ“… ๐Ÿš€ Jan 15 - The Legend of Heroes: Trails Beyond the Horizon ๐Ÿ“ฑ Jan 16 - BrokenLore: Unfollow ๐Ÿ›ฐ๏ธ Jan 20 - MIO: Memories in Orbit ๐ŸŒ‘ Jan 22 - Arknights: Endfield ๐Ÿช“ Jan 29 - I Hate This Place ๐Ÿง—๐Ÿฝโ€โ™€๏ธ Jan 29 - Cairn ๐Ÿง› Jan 30 - Code Vein II

PlayStation

453,344 views โ€ข 5 months ago

This month on PlayStation ๐Ÿ“… ๐Ÿš€ Jan 15 - The Legend of Heroes: Trails beyond the Horizon ๐Ÿ“ฑ Jan 16 - BrokenLore: Unfollow ๐Ÿ›ฐ๏ธ Jan 20 - MIO: Memories in Orbit ๐ŸŒ‘ Jan 22 - Arknights: Endfield ๐Ÿช“ Jan 29 - I Hate This Place ๐Ÿง—๐Ÿฝโ€โ™€๏ธ Jan 29 - Cairn ๐Ÿง› Jan 30 - Code Vein II
0:30

This month on PlayStation ๐Ÿ“… ๐Ÿš€ Jan 15 - The Legend of Heroes: Trails beyond the Horizon ๐Ÿ“ฑ Jan 16 - BrokenLore: Unfollow ๐Ÿ›ฐ๏ธ Jan 20 - MIO: Memories in Orbit ๐ŸŒ‘ Jan 22 - Arknights: Endfield ๐Ÿช“ Jan 29 - I Hate This Place ๐Ÿง—๐Ÿฝโ€โ™€๏ธ Jan 29 - Cairn ๐Ÿง› Jan 30 - Code Vein II

PlayStation Europe

24,866 views โ€ข 5 months ago

Jan-v2-VL-Max-Instruct is out on ๐Ÿ’› Our newest 30B vision-language model, extending the Jan-v2-VL family. This is our experiment bringing interleaved reasoning to an Instruct model. It handles long tasks well and stays on track when things get complicated. Good for research, multi-step problems, anything that needs patience. Try it now at
0:46

Jan-v2-VL-Max-Instruct is out on ๐Ÿ’› Our newest 30B vision-language model, extending the Jan-v2-VL family. This is our experiment bringing interleaved reasoning to an Instruct model. It handles long tasks well and stays on track when things get complicated. Good for research, multi-step problems, anything that needs patience. Try it now at

๐Ÿ‘‹ Jan

23,063 views โ€ข 5 months ago

On This Day in 2012, Super Jan Vertonghen signed for the club ๐Ÿ™Œ #THFC
0:39

On This Day in 2012, Super Jan Vertonghen signed for the club ๐Ÿ™Œ #THFC

COYS.com

18,983 views โ€ข 11 months ago

Introducing Cursor 2.0. Our first coding model and the best way to code with agents.
1:04

Introducing Cursor 2.0. Our first coding model and the best way to code with agents.

Cursor

3,559,238 views โ€ข 7 months ago

26th of Jan. National don't be a cnt day ๐Ÿ™‚.
0:26

26th of Jan. National don't be a cnt day ๐Ÿ™‚.

Gurridyula

173,071 views โ€ข 1 year ago

A look inside Jan Maluleke and his husband's wedding day.
0:22

A look inside Jan Maluleke and his husband's wedding day.

Musa Khawula

140,242 views โ€ข 6 months ago

Introducing TraceVLA: a fully open-source Vision-Language-Action model reimagining spatial-temporal awareness: โœจ 3.5x gains on real robots, SOTA in simulation ๐Ÿ’ก Fine-tunes on just 150K trajectories โšก Compact 4B model = 7B performance
0:29

Introducing TraceVLA: a fully open-source Vision-Language-Action model reimagining spatial-temporal awareness: โœจ 3.5x gains on real robots, SOTA in simulation ๐Ÿ’ก Fine-tunes on just 150K trajectories โšก Compact 4B model = 7B performance

Yongyuan Liang

39,378 views โ€ข 1 year ago

On repeat ๐Ÿ’™ ๐ŸŽต Jan Jan, Jan Jan Jan Jan Jan Jan Jan Vertonghen ... Toby, Toby Toby, Toby Toby, Toby Alderweireld ๐ŸŽต
0:26

On repeat ๐Ÿ’™ ๐ŸŽต Jan Jan, Jan Jan Jan Jan Jan Jan Jan Vertonghen ... Toby, Toby Toby, Toby Toby, Toby Alderweireld ๐ŸŽต

The Spurs Web

25,847 views โ€ข 1 year ago

This approach has made Sonnet the model of choice for developers worldwide. In addition to our new model, we're launching Claude Code, our first coding tool, in a limited research preview. With Claude Code, you can delegate substantial tasks to Claudeโ€”right from your terminal.
3:54

This approach has made Sonnet the model of choice for developers worldwide. In addition to our new model, we're launching Claude Code, our first coding tool, in a limited research preview. With Claude Code, you can delegate substantial tasks to Claudeโ€”right from your terminal.

Anthropic

1,139,786 views โ€ข 1 year ago

jan 29 2025 day 2 of album recording
1:01

jan 29 2025 day 2 of album recording

FLETCHER

25,767 views โ€ข 11 months ago