Groq Chat

An LPU inference engine

5.0•52 reviews•

874 followers

An LPU inference engine

5.0•52 reviews•

874 followers

Visit website

Predictive AI

•

AI Infrastructure Tools

A new type of end-to-end processing unit system that provides the fastest inference for computationally intensive applications with a sequential component to them, such as AI language applications (LLMs)

Viktor.comThe AI employee that does the work, in Slack & Teams

Promoted

Groq Chat Launches

Groq®Hyperfast LLM running on custom built GPUs

Launched on February 21st, 2024

Groq ChatWorld's fastest Large Language Model (LLM)

Launched on January 6th, 2024

Forum Threads

p/groq-chat

•

6mo ago

Nvidia to buy AI chip startup Groq’s assets for about $20 billion in largest deal on record

Merry Christmas Jonathan Ross (Groq s Founder)! $20B will buy a lot of holiday cheer!

Today, Groq announced that it has entered into a non-exclusive licensing agreement with Nvidia for Groq s inference technology. The agreement reflects a shared focus on expanding access to high-performance, low cost inference.

As part of this agreement, Jonathan Ross, Groq s Founder, Sunny Madra, Groq s President, and other members of the Groq team will join Nvidia to help advance and scale the licensed technology.

Groq will continue to operate as an independent company with Simon Edwards stepping into the role of Chief Executive Officer.

GroqCloud will continue to operate without interruption.

Source.

View all

5.0

Based on 52 reviews

Review Groq Chat?

Reviewers see Groq Chat as a speed-first tool that feels almost instant, especially for quick code fixes, rewrites, and short questions. The main appeal is fast back-and-forth with open models and easy model switching, while one founder from JDoodle.ai says they use Groq as an inference provider. The tradeoff, according to the user review, is weaker performance on long, involved reasoning, plus missing basics like saved chat history, longer context, clearer model guidance, and API access at the same speed.

+49

Summarized with AI

Pros

fast performance (19)

model selection (4)

real-time interaction (4)

open-source models (3)

API integration (2)

code generation (2)

reliable performance (2)

Cons

public API access (2)

Pros

Cons

Reviews

All Reviews

Most Informative

•29 reviews

What's great

fast performance (19)real-time interaction (4)code generation (2)model selection (4)open-source models (3)

The speed is the whole point. Replies come back almost instantly, even on the larger open models, so I never sit there watching it type. I use it for quick code fixes and rewriting text, and the fast back and forth changes how often I reach for it. Free to try, no setup, and being able to switch models is a nice bonus.

What needs improvement

public API access (2)longer context (1)saved chat history (1)

A few things. Saved chat history and longer context would help a lot. The model list shifts and it is not always clear which one to pick, so a one line note on each would go a long way. And public API access at the same speed, so I can build with it and not just chat in the window.

vs Alternatives

ChatGPT by OpenAI

Claude by Anthropic

I was already using ChatGPT and Claude for the same jobs. They are still better for long, involved reasoning, but for short questions they feel slow next to this now. I came to Groq for the speed and stayed because the open models handle most of my daily tasks fine, without me paying per message to find out.

Ratings

Ease of use

Reliability

Value for money

Customization

Report

6 views12d ago

used Groq Chat to build graph8

•5 reviews

We use Groq for ultra-fast inference when analyzing millions of contact records and enriching them with AI. It enables us to run deep research and structured reasoning at speeds that would be impossible on standard GPU setups. This level of performance lets us deliver intelligent outputs in real time, even at scale. We're grateful to the Groq team for building the kind of infrastructure that makes this possible.