Loading video...

Video Failed to Load

Go Home

A GPT-4 level chatbot, available to use completely free, running at over 800 tokens per second on Groq. I'm genuinely mindblown by LlaMA 3. Try it with the link in the next tweet.

rowancheung's profile picture

Rowan Cheung

596,415 subscribers

1,242,164 views • 2 years ago •via X (Twitter)

Science & TechnologyEducationNews & Politics
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

We are thrilled to be a launch partner for Meta Llama 3. Experience Llama 3 now at up to 350 tokens per second for Llama 3 8B and up to 150 tokens per second for Llama 3 70B, running in full FP16 precision on the Together API! 🤯
0:10

We are thrilled to be a launch partner for Meta Llama 3. Experience Llama 3 now at up to 350 tokens per second for Llama 3 8B and up to 150 tokens per second for Llama 3 70B, running in full FP16 precision on the Together API! 🤯

Together AI

88,229 views • 2 years ago

It's over. OpenAI just crushed it. We have their o3-level open-source model running on GroqInc 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 GroqInc 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

498,804 views • 1 year ago

🏎️ 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 views • 2 years ago

OpenAI DevDay is now finished. Here's what matters for creators: → dots: always-on agents powered by GPT-6 Astra → GPT-6.1 Sol, the most cost-efficient model → Up to 4K apps, including Magnific → UltraFast: responses at 300 tokens per second OpenAI x Magnific now available
0:14

OpenAI DevDay is now finished. Here's what matters for creators: → dots: always-on agents powered by GPT-6 Astra → GPT-6.1 Sol, the most cost-efficient model → Up to 4K apps, including Magnific → UltraFast: responses at 300 tokens per second OpenAI x Magnific now available

Magnific

11,138 views • 10 days ago

Nace shows Drex playing a strategy game. i gave it a harder opponent: my timeline Spoiler Guard sends each post to the new decision model and blurs the spoilers, 352 post checked in one session with sub-second calls → 128K context window, per Nace the first and only decision model at that size → #1 on the Decision Index, a Jev rival for $0.04 per 1M input tokens → no text generated, just a probability per post try it with 250M free tokens from Nace AI:
0:19

Nace shows Drex playing a strategy game. i gave it a harder opponent: my timeline Spoiler Guard sends each post to the new decision model and blurs the spoilers, 352 post checked in one session with sub-second calls → 128K context window, per Nace the first and only decision model at that size → #1 on the Decision Index, a Jev rival for $0.04 per 1M input tokens → no text generated, just a probability per post try it with 250M free tokens from Nace AI:

Israfil

12,350 views • 10 days ago

👀 Asking all the new GPT-4.1 models from OpenAI to draw… a pelican. Then comparing with Grok 3, LLaMA 4, and Gemini 2.5 Pro. Which one do you prefer? Try it yourself on 80+ models — 👇
0:11

👀 Asking all the new GPT-4.1 models from OpenAI to draw… a pelican. Then comparing with Grok 3, LLaMA 4, and Gemini 2.5 Pro. Which one do you prefer? Try it yourself on 80+ models — 👇

Pierre Valade

123,811 views • 1 year ago

Grok 4.5 performed GPT Sol level for free! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics demos Prompts: -robot deathmatch, Tombstone vs Minotaur -a hydraulic press flattening stuff on a conveyor -a semi truck jumping a canyon Outputs: GPT-5.6 Sol: 12.9K tokens, $0.51 (~7 min) Grok 4.5: 10.8K tokens, $0 (~5 min) Muse Spark 1.1: 26.8K tokens, $0.12 (~7.5 min) GLM 5.2: 10.9K tokens, $0.02 (~12 min) Grok 4.5 handled all three scenes genuinely well and got surprisingly close to GPT-5.6 this round. On top of that, it ran on the free tier. GPT-5.6 Sol, the frontier model, put out solid but not standout work. GLM 5.2 rendered all three scenes for pennies, but it came out the roughest of the four. Meta's new Muse Spark burned the most tokens yet still stayed cheap, delivering an average result.
0:18

Grok 4.5 performed GPT Sol level for free! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics demos Prompts: -robot deathmatch, Tombstone vs Minotaur -a hydraulic press flattening stuff on a conveyor -a semi truck jumping a canyon Outputs: GPT-5.6 Sol: 12.9K tokens, $0.51 (~7 min) Grok 4.5: 10.8K tokens, $0 (~5 min) Muse Spark 1.1: 26.8K tokens, $0.12 (~7.5 min) GLM 5.2: 10.9K tokens, $0.02 (~12 min) Grok 4.5 handled all three scenes genuinely well and got surprisingly close to GPT-5.6 this round. On top of that, it ran on the free tier. GPT-5.6 Sol, the frontier model, put out solid but not standout work. GLM 5.2 rendered all three scenes for pennies, but it came out the roughest of the four. Meta's new Muse Spark burned the most tokens yet still stayed cheap, delivering an average result.

atomic.chat

70,490 views • 3 months ago

Matt Olson was running 26.6 feet per second, over a foot per second higher than his season average, and never stopped running as he picked up the first base coach and made the turn at 1st But I admire your INSISTENCE it was Olson's fault despite being utterly, completely wrong
0:16

Matt Olson was running 26.6 feet per second, over a foot per second higher than his season average, and never stopped running as he picked up the first base coach and made the turn at 1st But I admire your INSISTENCE it was Olson's fault despite being utterly, completely wrong

Lindsay Crosby, big baseball guy

80,111 views • 4 months ago

Nemotron 3 Ultra performed GPT 5.5 level 10× cheaper We gave three same prompts to build HTML5 canvas with real physics. At first scene we have water in a spinning drum. Galton board - balls through pegs into bins. And a block collision setup with extreme mass differences. Outputs: Nemotron 3 Ultra: 11.3k tokens, $0.051 GPT 5.5: 11.0k tokens, $0.57 Nemotron stays right on GPT 5.5's heels, but at 10× cheaper. The gap in quality is far smaller than the gap in price.
0:15

Nemotron 3 Ultra performed GPT 5.5 level 10× cheaper We gave three same prompts to build HTML5 canvas with real physics. At first scene we have water in a spinning drum. Galton board - balls through pegs into bins. And a block collision setup with extreme mass differences. Outputs: Nemotron 3 Ultra: 11.3k tokens, $0.051 GPT 5.5: 11.0k tokens, $0.57 Nemotron stays right on GPT 5.5's heels, but at 10× cheaper. The gap in quality is far smaller than the gap in price.

atomic.chat

701,864 views • 4 months ago

A 15-second shot, created with Pika 1.0! לב started with Text-to-Video, then extended 3 times using the ‘Add 4 Sec’ button. Try it at
0:15

A 15-second shot, created with Pika 1.0! לב started with Text-to-Video, then extended 3 times using the ‘Add 4 Sec’ button. Try it at

Pika

40,451 views • 2 years ago

New Claude Sonnet 5 performs at GPT 5.5 level 6x cheaper! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics crash demos Prompts: - A car crashes into a brick wall - A wrecking ball destroys a house - A catapult throws a rock at a castle wall Outputs: Sonnet 5: 15,047 tokens, $0.15 Opus 4.8: 23,063 tokens, $0.58 Sonnet 4.6: 25,824 tokens, $0.39 GPT 5.5: 31,152 tokens, $0.94 Sonnet 5 did as well as Opus 4.8 and GPT 5.5 on all three tests. In the wrecking ball test, it beat Opus 4.8. The cable moves smoothly and every hit connects. In the catapult test, it beat GPT 5.5. The rock always lands inside the wall. Sonnet 5 still needs better detail and graphics. But it used fewer tokens than every other model
0:18

New Claude Sonnet 5 performs at GPT 5.5 level 6x cheaper! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics crash demos Prompts: - A car crashes into a brick wall - A wrecking ball destroys a house - A catapult throws a rock at a castle wall Outputs: Sonnet 5: 15,047 tokens, $0.15 Opus 4.8: 23,063 tokens, $0.58 Sonnet 4.6: 25,824 tokens, $0.39 GPT 5.5: 31,152 tokens, $0.94 Sonnet 5 did as well as Opus 4.8 and GPT 5.5 on all three tests. In the wrecking ball test, it beat Opus 4.8. The cable moves smoothly and every hit connects. In the catapult test, it beat GPT 5.5. The rock always lands inside the wall. Sonnet 5 still needs better detail and graphics. But it used fewer tokens than every other model

atomic.chat

730,766 views • 3 months ago

Our second NFT mint is live on Galxe. Holders who had at least 1 $WOJAK in an on-chain wallet can mint for free. We cover the gas. This was designed by one of our community members. Link and mint instructions in the next tweet in this thread.
0:11

Our second NFT mint is live on Galxe. Holders who had at least 1 $WOJAK in an on-chain wallet can mint for free. We cover the gas. This was designed by one of our community members. Link and mint instructions in the next tweet in this thread.

Wojak

67,340 views • 3 years ago

LongCat performed Opus 4.8 and GPT 5.5 level on real physics tasks for $0! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics Prompts: - A cannon demolishing a brick wall - A bowling ball knocking down the pins - A tornado that sucks in random objects Outputs: LongCat: 18,015 tokens, $0.00 Opus 4.8: 18,872 tokens, $0.48 GPT 5.5: 32,588 tokens, $0.98 GLM 5.2: 31,062 tokens, $0.09 On the physics LongCat came out ahead of Opus 4.8 and GLM 5.2 - cleaner collisions, nothing clipping or falling through. On detail and rendering it matched GPT 5.5, the best looking of the four. Getting this quality for free is wild!
0:16

LongCat performed Opus 4.8 and GPT 5.5 level on real physics tasks for $0! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics Prompts: - A cannon demolishing a brick wall - A bowling ball knocking down the pins - A tornado that sucks in random objects Outputs: LongCat: 18,015 tokens, $0.00 Opus 4.8: 18,872 tokens, $0.48 GPT 5.5: 32,588 tokens, $0.98 GLM 5.2: 31,062 tokens, $0.09 On the physics LongCat came out ahead of Opus 4.8 and GLM 5.2 - cleaner collisions, nothing clipping or falling through. On detail and rendering it matched GPT 5.5, the best looking of the four. Getting this quality for free is wild!

atomic.chat

105,523 views • 3 months ago

ROCKET PERPS ARE NOW AVAILABLE TO PLAY FOR FREE 🚀 1000x perps with a one-tap interface. Try for free on trial mode on the link below. Hit profit on 3 in a row = earn deposit match of $15. Can you beat the trial challenge?
0:20

ROCKET PERPS ARE NOW AVAILABLE TO PLAY FOR FREE 🚀 1000x perps with a one-tap interface. Try for free on trial mode on the link below. Hit profit on 3 in a row = earn deposit match of $15. Can you beat the trial challenge?

Defi App

370,761 views • 4 months ago

China f*cked the world again DeepSeek just dropped a killer library that saves up to 98% on tokens ur GPT Astra and Opus 5.5 it's DeepGEMM, the engine DeepSeek trains and runs its own models on faster GPU math -> more tokens per GPU -> cheaper tokens > plug the engine DeepSeek uses into your own models > squeeze more tokens per second out of the GPUs you already pay for > match or beat expert-tuned GPU libraries on speed u will pay $1.6 instead of $50 its sitting in one public repo, link below
0:15

China f*cked the world again DeepSeek just dropped a killer library that saves up to 98% on tokens ur GPT Astra and Opus 5.5 it's DeepGEMM, the engine DeepSeek trains and runs its own models on faster GPU math -> more tokens per GPU -> cheaper tokens > plug the engine DeepSeek uses into your own models > squeeze more tokens per second out of the GPUs you already pay for > match or beat expert-tuned GPU libraries on speed u will pay $1.6 instead of $50 its sitting in one public repo, link below

Mnimiy

429,720 views • 5 days ago

Pakistan Army's air defence battery which was trying to shoot the drone hovering over it in Lahore skies targeted and blasted with precision by the same drone. Check the buildings in the background. This is next level warfare by Indian Army. Second video courtesy: War & Gore
0:19

Pakistan Army's air defence battery which was trying to shoot the drone hovering over it in Lahore skies targeted and blasted with precision by the same drone. Check the buildings in the background. This is next level warfare by Indian Army. Second video courtesy: War & Gore

Divya Kumar Soti

559,150 views • 1 year ago