Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

WOW. Mercury coder feels almost as fast as models on Groq, but it runs on consumer hardware. Just wait till the Groq Inc team gets this on their platform... you'll be able to generate nicely-sized codebases in seconds. It's going to be insane.

mattshumer_'s profile picture

Matt Shumer

94,624 subscribers

42,595 Aufrufe • vor 1 Jahr •via X (Twitter)

Wissenschaft & TechnologieBildung
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

I am testing LLaMA 2 on Groq hardware and it has blown my mind! NOTHING is this fast. Working on getting the hardware local for testing my new open source models. More soon…
0:18

I am testing LLaMA 2 on Groq hardware and it has blown my mind! NOTHING is this fast. Working on getting the hardware local for testing my new open source models. More soon…

Brian Roemmele

55,251 Aufrufe • vor 2 Jahren

It's over. OpenAI just crushed it. We have their o3-level open-source model running on Groq Inc at 500 tokens per second. Watch it build an entire SaaS app in just a few seconds. This is the new standard. Why the hell would you use anything else??
0:16

It's over. OpenAI just crushed it. We have their o3-level open-source model running on Groq Inc at 500 tokens per second. Watch it build an entire SaaS app in just a few seconds. This is the new standard. Why the hell would you use anything else??

Matt Shumer

498,609 Aufrufe • vor 10 Monaten

Trump on cannabis: "You'll be able to see if it is as good as people say it is. I mean, people say it is beyond good. And you'll be able to find that out now."
0:14

Trump on cannabis: "You'll be able to see if it is as good as people say it is. I mean, people say it is beyond good. And you'll be able to find that out now."

The Bulwark

15,990 Aufrufe • vor 6 Monaten

The RWA Inc. Trading Platform is launching mid July. DEX and Swap integrations are already completed and they’ll be fully included in the July release. You’ll be able to trade live on the RWA Inc. Investor Platform. More features coming soon as more clients get ready to list. 👉
0:14

The RWA Inc. Trading Platform is launching mid July. DEX and Swap integrations are already completed and they’ll be fully included in the July release. You’ll be able to trade live on the RWA Inc. Investor Platform. More features coming soon as more clients get ready to list. 👉

RWA Inc.

21,822 Aufrufe • vor 11 Monaten

You'll be able to generate infinite variation of terrains in seconds with my Landscape Brushes™ Not just earth-like scenery.
0:18

You'll be able to generate infinite variation of terrains in seconds with my Landscape Brushes™ Not just earth-like scenery.

FR3NKD

20,229 Aufrufe • vor 1 Monat

how it feels to be a newgen but the algorithm has recognized my interest just enough to put random discourse on my timeline without me being able to know what any of it means or whats going on
0:12

how it feels to be a newgen but the algorithm has recognized my interest just enough to put random discourse on my timeline without me being able to know what any of it means or whats going on

turd

123,492 Aufrufe • vor 5 Monaten

In #MHStories3, you'll be be able to soar through the skies on flying monsties as you take in the view! Something catch your eye? Head on over there and see what awaits!
0:18

In #MHStories3, you'll be be able to soar through the skies on flying monsties as you take in the view! Something catch your eye? Head on over there and see what awaits!

Monster Hunter

355,385 Aufrufe • vor 8 Monaten

Just wanted to add, also try it out with Matcaps 👓 It's not going to be as perfect as using nodes, but it can add a bit of stylization to the reflection (but def check out Luwke's node settings on his post!)
0:11

Just wanted to add, also try it out with Matcaps 👓 It's not going to be as perfect as using nodes, but it can add a bit of stylization to the reflection (but def check out Luwke's node settings on his post!)

mokunachoi🐉 3D Comms Waitlist OPEN

32,763 Aufrufe • vor 8 Monaten

How it feels to finally be able to say nigger on the TL
0:17

Sensitive content

How it feels to finally be able to say nigger on the TL

Sam - Quality Learing Center Graduate

25,476 Aufrufe • vor 1 Monat

🏎️ Incredible Speeds with Groq's LPU-Powered Inference 🕔 The langchain-groq package exposes inference capabilities powered by Groq Inc's Language Processing Units (LPUs), soaring to new heights with up to 500 tokens per second on this Mistral AI Mixtral model. Welcome to the fast lane of language processing!
0:16

🏎️ Incredible Speeds with Groq's LPU-Powered Inference 🕔 The langchain-groq package exposes inference capabilities powered by Groq Inc's Language Processing Units (LPUs), soaring to new heights with up to 500 tokens per second on this Mistral AI Mixtral model. Welcome to the fast lane of language processing!

LangChain

27,387 Aufrufe • vor 2 Jahren

Introducing Groq Web Crawler Bot 🤖 Easily scrape websites, summarize content, analyze sentiment, and extract key topics using Firecrawl and Groq Inc APIs Just enter a URL, and it will scrape the entire page to deliver the output you need. Check it out:
0:12

Introducing Groq Web Crawler Bot 🤖 Easily scrape websites, summarize content, analyze sentiment, and extract key topics using Firecrawl and Groq Inc APIs Just enter a URL, and it will scrape the entire page to deliver the output you need. Check it out:

Eric Ciarla (hiring)

28,201 Aufrufe • vor 1 Jahr

Wild. Llama 4 Maverick just went Beast Mode 🔥 SambaNova partnered with AI at Meta to deliver the fastest Llama 4 inference on the market. Even the mighty Groq Inc can’t keep up! Let’s dive in ↓
0:15

Wild. Llama 4 Maverick just went Beast Mode 🔥 SambaNova partnered with AI at Meta to deliver the fastest Llama 4 inference on the market. Even the mighty Groq Inc can’t keep up! Let’s dive in ↓

Charly Wargnier

36,463 Aufrufe • vor 1 Jahr

Google is making progress on their diffusion models... It's now as good as a Gemini 2.0 Flash Lite. The writing is on the wall, a majority of language AI use in the future will be diffusion models.
0:14

Google is making progress on their diffusion models... It's now as good as a Gemini 2.0 Flash Lite. The writing is on the wall, a majority of language AI use in the future will be diffusion models.

Carlos E. Perez

193,952 Aufrufe • vor 5 Monaten

Who said TPUs can't be fast! This is roughly Groq speeds out of TPU 8i, but with Gemini Flash model so far more intelligent
0:17

Who said TPUs can't be fast! This is roughly Groq speeds out of TPU 8i, but with Gemini Flash model so far more intelligent

Max Weinbach

785,631 Aufrufe • vor 1 Monat

Super excited to be featured in the Nike SNKRS app as their artist for “This Week in SNKRS”. Catch me on there till the end of the week!
0:16

Super excited to be featured in the Nike SNKRS app as their artist for “This Week in SNKRS”. Catch me on there till the end of the week!

Ra Kazadi

26,494 Aufrufe • vor 3 Jahren

You used to be able to just create a Native GUI App in 10 seconds. No Electron, no Game Engines, no Web frameworks. Just a lean fast .EXE produced in seconds. Works on any Windows machine WITHOUT Internet connection. Software Development is actually going backwards.
0:16

You used to be able to just create a Native GUI App in 10 seconds. No Electron, no Game Engines, no Web frameworks. Just a lean fast .EXE produced in seconds. Works on any Windows machine WITHOUT Internet connection. Software Development is actually going backwards.

Тsфdiиg

2,143,834 Aufrufe • vor 6 Monaten

Using Groq Inc to instantly refactor and document code. The implications for software engineering are wild. Gone are the days of waiting on an LLM for suggestions or code changes. Now, it's an instant feedback loop. Demo link in the comments:
0:16

Using Groq Inc to instantly refactor and document code. The implications for software engineering are wild. Gone are the days of waiting on an LLM for suggestions or code changes. Now, it's an instant feedback loop. Demo link in the comments:

Matt Shumer

571,484 Aufrufe • vor 2 Jahren

This is what 200 tokens/second looks like with Kimi K2 on Groq Inc For reference, Claude Sonnet-4 is usually delivered at ~60 TPS
0:19

This is what 200 tokens/second looks like with Kimi K2 on Groq Inc For reference, Claude Sonnet-4 is usually delivered at ~60 TPS

Cline

100,719 Aufrufe • vor 11 Monaten