• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
AI
Announcement

OpenAI's GPT6.1 Sol Ultrafast reportedly runs on Nvidia GPUs, not Cerebras

SemiAnalysis claims the model is running at a low batch size on Nvidia GPUs and asks whether Cerebras might serve it later.

Sam AltmanSA
10 Sources, 11d ago, first seen 11d ago

TLDR

SemiAnalysis claims OpenAI's latest GPT6.1 Sol Ultrafast is running at a low batch size on Nvidia GPUs, not Cerebras. It asks whether Cerebras will serve the model in the future.

Combined views

1.2M

10 Sources, first seen 11d ago

7.7K likes510 comments563 saves331 reposts

Combined views

1.2M

10 Sources, first seen 11d ago

7.7K likes510 comments563 saves331 reposts

Sentiment

Positive53.6%46.4%Negative

Summary

Positive accounts welcomed OpenAI's Ultrafast speeds on NVIDIA GPUs for hardware clarity and agent potential, while negative replies criticized the high cost relative to gains and questioned long-term efficiency.

Based on 94 sentiment-bearing replies from 89 accounts across 3 conversations.

Featured Source

Sentiment

Positive53.6%46.4%Negative

Summary

Positive accounts welcomed OpenAI's Ultrafast speeds on NVIDIA GPUs for hardware clarity and agent potential, while negative replies criticized the high cost relative to gains and questioned long-term efficiency.

Based on 94 sentiment-bearing replies from 89 accounts across 3 conversations.

Related

Codex adds beta next-message suggestions for Pro users

OpenAI says the feature uses your conversation and how you talk to Codex to suggest what to say next.

OpenAI Rolls Out "Ultrafast" Mode for GPT-6.1 Sol

OpenAI says the mode offers up to 8x faster speeds than Sol Standard in the API, Codex, and ChatGPT Work.

OpenAI Rolls Out "Ultrafast" Mode for GPT-6.1 Sol
OpenAI’s $50B versus $70B revenue debate and AI infrastructure demand

One post questions how much revenue OpenAI keeps after partners take a cut and argues token growth matters more.

10 Sources

SemiAnalysis@SemiAnalysis_ALERT 🚨🚨OpenAI's latest GPT6.1 Sol Ultrafast is NOT running on Cerebras but is instead running at a low batch size on NVIDIA GPUs. What does this say about Cerebras? Will Cerebras be serving GPT6.1 Sol Ultrafast in the future?11d
sunny madra@sundeep👀👀👀11d
Chubby♨️@kimmonismusOpenAI announced up to 300 tokens per second with Ultrafast. According to SemiAnalysis, it’s running on NVIDIA GPUs. That’s particularly interesting given its partnership with Cerebras specifically for ultra-low-latency inference. According to SemiAnalysis, OpenAI is using NVIDIA GPUs at a low batch size, prioritizing speed for individual requests.10d
tae kim@firstadopterCerebras should comment publicly, especially since insiders are dumping stock and they hyped GPT-5.6 Sol Ultrafast win LAST MONTH. Was it a capacity issue? Are yields the problem? The silence is deafening.10d
Sam Altman@samaThere is some speculation about our partnership with Cerebras. Cerebras is a close partner, and we have a deep engagement pushing on the frontiers of speed.8d
Rohan Paul@rohanpaul_ai@sama8d
Andrew Feldman@andrewdfeldmanThanks @sama . We are excited to be building extraordinary things and blazing speeds with @OpenAI8d
Sarah Chieng@MilksandMatchatag the folks who need to read this8d
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    OpenAICerebras

    10 Sources

    SemiAnalysis@SemiAnalysis_ALERT 🚨🚨OpenAI's latest GPT6.1 Sol Ultrafast is NOT running on Cerebras but is instead running at a low batch size on NVIDIA GPUs. What does this say about Cerebras? Will Cerebras be serving GPT6.1 Sol Ultrafast in the future?11d
    sunny madra@sundeep👀👀👀11d
    Chubby♨️@kimmonismusOpenAI announced up to 300 tokens per second with Ultrafast. According to SemiAnalysis, it’s running on NVIDIA GPUs. That’s particularly interesting given its partnership with Cerebras specifically for ultra-low-latency inference. According to SemiAnalysis, OpenAI is using NVIDIA GPUs at a low batch size, prioritizing speed for individual requests.10d
    tae kim@firstadopterCerebras should comment publicly, especially since insiders are dumping stock and they hyped GPT-5.6 Sol Ultrafast win LAST MONTH. Was it a capacity issue? Are yields the problem? The silence is deafening.10d
    Sam Altman@samaThere is some speculation about our partnership with Cerebras. Cerebras is a close partner, and we have a deep engagement pushing on the frontiers of speed.8d
    Rohan Paul@rohanpaul_ai@sama8d
    Andrew Feldman@andrewdfeldmanThanks @sama . We are excited to be building extraordinary things and blazing speeds with @OpenAI8d
    Sarah Chieng@MilksandMatchatag the folks who need to read this8d
    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet