Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

State → local decision model → action Check out Liquid AI's d1 decision model playing Lmmy Run, all on its own 🦖👾 Served 100% on-device, making decisions in a fraction of a second

lmstudiodevs's profile picture

LM Studio Developers

3,179 subscribers

20,131 Aufrufe • vor 15 Tagen •via X (Twitter)

Wissenschaft & TechnologieGaming
LIVE

Anya Rossi• Live Now

Private livecam show

5 Kommentare

Profilbild von LM Studio Developers
LM Studio Developersvor 15 Tagen

Stack used for the demo: Model server - @lmstudio Model - d1 by @liquidai Inference runtime - @llama_cpp Lmmy Run is based on Check out the docs for how to do it yourself!

Profilbild von Alex
Alexvor 15 Tagen

@liquidai Cool to see d1 on llama.cpp. makes me wanna revise d1 again perhaps on a different framework.

Profilbild von Revertron
Revertronvor 15 Tagen

@liquidai On Windows when something is animated, like even the answer is streaming in the chat, the tokens per second drop by substantial amount. Can you fix it? I use Radeon AI PRO R9700 as a second dedicated GPU for inference, but that doesn't matter.

Profilbild von Iris晴柔
Iris晴柔vor 15 Tagen

@liquidai running a decision model 100% on-device at sub-second latency — that's the part everyone said was still years out. local models are catching up fast

Profilbild von T.Rex-Baby
T.Rex-Babyvor 15 Tagen

@liquidai Leave me 🦖 out of your 🦀

Ähnliche Videos

Local Liquid d1 3B crushed OpenAI Decision at Snake 🐍 Liquid AI d1 on a single RTX 3090 decides in 8 ms so its snake made 82 moves a second and ate 86 apples while OpenAI's API took 345 ms a call and ate 3 Run decision models ->
0:22

Local Liquid d1 3B crushed OpenAI Decision at Snake 🐍 Liquid AI d1 on a single RTX 3090 decides in 8 ms so its snake made 82 moves a second and ate 86 apples while OpenAI's API took 345 ms a call and ate 3 Run decision models ->

atomic.chat

194,947 Aufrufe • vor 21 Tagen

Ollama now supports Jev-like decision models all locally. Use decision models like Nimble for tasks like ticket triaging, model routing, and content moderation. ollama pull nimble Here’s Nimble playing Ollama racer through the new local /v1/systemone API by making decisions in real-time. 🏎️
0:23

Ollama now supports Jev-like decision models all locally. Use decision models like Nimble for tasks like ticket triaging, model routing, and content moderation. ollama pull nimble Here’s Nimble playing Ollama racer through the new local /v1/systemone API by making decisions in real-time. 🏎️

ollama

667,164 Aufrufe • vor 29 Tagen

The open-source local version of Laya crushes Jev in response speed! On the left is Laya, a local 421M open-source decision model. On the right is Jev 1.13.0, running through a cloud API. Same Snake game, same typed decisions, and the same 30-second free run: - Laya: Score 46, Length 52, 86.5 decisions/sec - Jev: Score 1, Length 7, 3.2 decisions/sec - In a real test on an M5 Pro, median latency was 15.3ms locally versus 298.1ms in the cloud, so nearly 20x faster. Laya uses around 1GB of memory, responds in milliseconds, and doesn’t depend on a network connection. While Jev waits for a cloud round-trip at every step, Laya makes each decision instantly on-device.
0:31

The open-source local version of Laya crushes Jev in response speed! On the left is Laya, a local 421M open-source decision model. On the right is Jev 1.13.0, running through a cloud API. Same Snake game, same typed decisions, and the same 30-second free run: - Laya: Score 46, Length 52, 86.5 decisions/sec - Jev: Score 1, Length 7, 3.2 decisions/sec - In a real test on an M5 Pro, median latency was 15.3ms locally versus 298.1ms in the cloud, so nearly 20x faster. Laya uses around 1GB of memory, responds in milliseconds, and doesn’t depend on a network connection. While Jev waits for a cloud round-trip at every step, Laya makes each decision instantly on-device.

Simplifying AI

24,406 Aufrufe • vor 1 Monat

Introducing Decision-Bench, a new industry standard for measuring model capabilities in making ROI-positive decisions on messy enterprise data. Every enterprise has slowed AI investments due to no ROI; AIs still fail at complex decisions, and pricing second order effects.
1:06

Introducing Decision-Bench, a new industry standard for measuring model capabilities in making ROI-positive decisions on messy enterprise data. Every enterprise has slowed AI investments due to no ROI; AIs still fail at complex decisions, and pricing second order effects.

ethan ding 📊

14,561 Aufrufe • vor 15 Tagen

Introducing THIS / THAT Model 1.0. Trained by FLock. Not another chatbot. A best-in-class open-source model built to decide. 94.1% success rate on our 68-question decision test, outperforming GPT-5.6, Deepseek-4.1-flash, Kimi K3, Jev, and more. Just 1.9B parameters. Runs locally. Measured decision latency of ~31 ms on an RTX 5080 laptop GPU. We’re putting decentralized AI to work: giving developers and AI agents decision-making capabilities they can run on their own hardware. Your model. Your machine. Not every decision needs the cloud.
0:20

Introducing THIS / THAT Model 1.0. Trained by FLock. Not another chatbot. A best-in-class open-source model built to decide. 94.1% success rate on our 68-question decision test, outperforming GPT-5.6, Deepseek-4.1-flash, Kimi K3, Jev, and more. Just 1.9B parameters. Runs locally. Measured decision latency of ~31 ms on an RTX 5080 laptop GPU. We’re putting decentralized AI to work: giving developers and AI agents decision-making capabilities they can run on their own hardware. Your model. Your machine. Not every decision needs the cloud.

FLock.io

12,708 Aufrufe • vor 1 Monat

The NAIA has a decision to make... D2 made their move to mirror the D1 model. Does NAIA keep their decision tabled until April or do they decide to make their decisions now as well?
1:27

The NAIA has a decision to make... D2 made their move to mirror the D1 model. Does NAIA keep their decision tabled until April or do they decide to make their decisions now as well?

NAIA Hoops Report

55,016 Aufrufe • vor 2 Monaten

You can now run pplx-decider-flash-v1.2 locally on your Mac, without an API key. Decider for Mac is an app that runs the 4B decision model on device. Ask a question about text or an image and get a probability back, all on your machine.
0:51

You can now run pplx-decider-flash-v1.2 locally on your Mac, without an API key. Decider for Mac is an app that runs the 4B decision model on device. Ask a question about text or an image and get a probability back, all on your machine.

Perplexity Developers

98,521 Aufrufe • vor 6 Tagen

“There are three decisions in life: a good decision, a bad decision and no decision.” We celebrate good calls and we learn from bad ones. But standing still is the real danger. Will Greenwood on decision-making on and off the rugby pitch.
0:45

“There are three decisions in life: a good decision, a bad decision and no decision.” We celebrate good calls and we learn from bad ones. But standing still is the real danger. Will Greenwood on decision-making on and off the rugby pitch.

Omni™

6,473,107 Aufrufe • vor 7 Monaten

Liquid AI's head of post-training explained how they built a small model that runs on-device under 1 GB in 20 minutes - better than $2500 small-model bootcamps. pick LFM2.5 base -> on-policy preference alignment -> agentic reinforcement learning -> curriculum training -> iterative model merging -> ship a 1B model that reliably calls tools on your phone. That loop is why frontier small models now beat 70B models on the tasks that actually matter. LFM2.5 + on-policy DPO + agentic RL + curriculum training + iterative merging - that's the stack. Watch and save it, then run a 1B agent on your phone tonight.
19:11

Liquid AI's head of post-training explained how they built a small model that runs on-device under 1 GB in 20 minutes - better than $2500 small-model bootcamps. pick LFM2.5 base -> on-policy preference alignment -> agentic reinforcement learning -> curriculum training -> iterative model merging -> ship a 1B model that reliably calls tools on your phone. That loop is why frontier small models now beat 70B models on the tasks that actually matter. LFM2.5 + on-policy DPO + agentic RL + curriculum training + iterative merging - that's the stack. Watch and save it, then run a 1B agent on your phone tonight.

h100envy

87,975 Aufrufe • vor 3 Monaten

NEW: Google releases EmbeddingGemma, a state-of-the-art multilingual embedding model perfect for on-device use cases! At only 308M params, the model can run 100% locally in your browser! 🤯 Explore your documents in an interactive 3D universe with our demo: "The Semantic Galaxy"
1:12

NEW: Google releases EmbeddingGemma, a state-of-the-art multilingual embedding model perfect for on-device use cases! At only 308M params, the model can run 100% locally in your browser! 🤯 Explore your documents in an interactive 3D universe with our demo: "The Semantic Galaxy"

Xenova

23,338 Aufrufe • vor 1 Jahr

ICYMI: the last month’s biggest local AI model drops... Check out the latest—all ready to run locally on your RTX AI PC.
1:54

ICYMI: the last month’s biggest local AI model drops... Check out the latest—all ready to run locally on your RTX AI PC.

NVIDIA RTX Spark

145,162 Aufrufe • vor 10 Monaten

Introducing Mercury Decide: the most intelligent decision model on OpenRouter (JevBench v1.4) and one of the fastest. Up to 14 decisions per second. Watch it go head-to-head with Jev in chess. Free for early access on OpenRouter:
1:33

Introducing Mercury Decide: the most intelligent decision model on OpenRouter (JevBench v1.4) and one of the fastest. Up to 14 decisions per second. Watch it go head-to-head with Jev in chess. Free for early access on OpenRouter:

Inception

20,209 Aufrufe • vor 28 Tagen

Video: Decision model trained in ~2 mins on a single DGX Spark using Unsloth! Qwen3.5-2B as base model. Just follow instruction here:
1:56

Video: Decision model trained in ~2 mins on a single DGX Spark using Unsloth! Qwen3.5-2B as base model. Just follow instruction here:

Ivan Fioravanti

24,208 Aufrufe • vor 19 Tagen

Must Add Action Turkey / Olympiacos .5 Decision Making Get 2 on the 🏀 ✅ Stampede ✅ Make .5 Decisions ✅
1:07

Must Add Action Turkey / Olympiacos .5 Decision Making Get 2 on the 🏀 ✅ Stampede ✅ Make .5 Decisions ✅

Dustin Aubert

11,488 Aufrufe • vor 1 Jahr

Introducing d3-turbo: our newest state-of-the-art multimodal foundation decision model⚡ #1 on both Jev Decision Index boards. It points(box), follows and sees images in your questions. StateOnce brings 15x faster than d3 flash 🤗 #vLLM #Jev #Decision
0:41

Introducing d3-turbo: our newest state-of-the-art multimodal foundation decision model⚡ #1 on both Jev Decision Index boards. It points(box), follows and sees images in your questions. StateOnce brings 15x faster than d3 flash 🤗 #vLLM #Jev #Decision

Xunzhuo

20,973 Aufrufe • vor 9 Tagen

Local Laya moggs Jev at Grok 4.7-built Tetris 🧩 An open-weights System One model called Laya, beat cloud-based Jev at playing Tetris by making decisions 11 times faster, running locally on a 16GB MacBook Air! Run AI models locally ->
0:22

Local Laya moggs Jev at Grok 4.7-built Tetris 🧩 An open-weights System One model called Laya, beat cloud-based Jev at playing Tetris by making decisions 11 times faster, running locally on a 16GB MacBook Air! Run AI models locally ->

atomic.chat

1,101,104 Aufrufe • vor 1 Monat

Early on in my career, I had one business and I was still figuring it out. The decisions in front of me felt like everything was on the line. I needed a model. Something that could make every call clearer, big or small. What I figured out: all decision-making is value clarification. It comes down to what’s most important to you. Two people can look at the same situation and make completely different calls. Both right. Because the answer always comes back to what you value most. Next time a decision doesn’t feel clear, run it through OOC-EMR.
2:14

Early on in my career, I had one business and I was still figuring it out. The decisions in front of me felt like everything was on the line. I needed a model. Something that could make every call clearer, big or small. What I figured out: all decision-making is value clarification. It comes down to what’s most important to you. Two people can look at the same situation and make completely different calls. Both right. Because the answer always comes back to what you value most. Next time a decision doesn’t feel clear, run it through OOC-EMR.

Tony Robbins

62,770 Aufrufe • vor 5 Monaten

Decision models are moving into enterprise workflows. That company data must stay private. Now it can. Introducing the first private decision model, inside a TEE. Sage is now live on NEAR AI’s confidential infrastructure. Private decisions, at machine speed.
0:20

Decision models are moving into enterprise workflows. That company data must stay private. Now it can. Introducing the first private decision model, inside a TEE. Sage is now live on NEAR AI’s confidential infrastructure. Private decisions, at machine speed.

Levanto Labs

19,368 Aufrufe • vor 3 Tagen

【 Sliggy stream mascot showcase 】 I'm excited to share that I worked on Sliggy's Vtuber model!! Here's a full showcase of all the outfits and animations, I hope everyone in chat enjoys them ❤️ Check out the streams to see the slug in action 👀 #Live2D Liquid Sliggy
1:24

【 Sliggy stream mascot showcase 】 I'm excited to share that I worked on Sliggy's Vtuber model!! Here's a full showcase of all the outfits and animations, I hope everyone in chat enjoys them ❤️ Check out the streams to see the slug in action 👀 #Live2D Liquid Sliggy

Emii 🩷 VCT LONDON

44,585 Aufrufe • vor 1 Jahr