Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

OpenAI-GPT-20B runs at 9 tokens per second on a 10 year old CPU (4-core i7-6700k) Could get up to 50 000 token context too.

nisten's profile picture

nisten🇨🇦e/acc

17,864 subscribers

12,274 Aufrufe • vor 1 Jahr •via X (Twitter)

Wissenschaft & TechnologieNachrichten & Politik
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Live on Cline (v3.67.1) OpenAI 's GPT 5.3 Codex. The speed and token efficiency improvements are real. Here is what's new: > 25% faster than 5.2 Codex > #1 on SWE-Bench Pro (4 different programming languages) > Fewer tokens per task than any prior OpenAI model Runs cost less and finish faster. You can use it in Cline right now without setting up an API key. Select the model and try it on your repo.
0:31

Live on Cline (v3.67.1) OpenAI 's GPT 5.3 Codex. The speed and token efficiency improvements are real. Here is what's new: > 25% faster than 5.2 Codex > #1 on SWE-Bench Pro (4 different programming languages) > Fewer tokens per task than any prior OpenAI model Runs cost less and finish faster. You can use it in Cline right now without setting up an API key. Select the model and try it on your repo.

Cline

21,291 Aufrufe • vor 5 Monaten

🚨The SEC may soon dismiss its lawsuit against Ripple (#XRP), following the ConsenSys case dismissal! XRP’s price could surge to $10-$18 after this announcement! This boosts decentralized finance (DeFi) growth on #XRPL. CTF Token, the leading DeFi token, is showing strong bullish momentum. With a $20B market cap, CTF could skyrocket from $0.78 to $748.50 per token! CTF Token’s limited supply (119M tokens) will drive its value higher! CTF Token is set to explode! Do your own research (DYOR). CTF Token trading: CTF token trade link on MEXC: Website:
1:15

🚨The SEC may soon dismiss its lawsuit against Ripple (#XRP), following the ConsenSys case dismissal! XRP’s price could surge to $10-$18 after this announcement! This boosts decentralized finance (DeFi) growth on #XRPL. CTF Token, the leading DeFi token, is showing strong bullish momentum. With a $20B market cap, CTF could skyrocket from $0.78 to $748.50 per token! CTF Token’s limited supply (119M tokens) will drive its value higher! CTF Token is set to explode! Do your own research (DYOR). CTF Token trading: CTF token trade link on MEXC: Website:

JackTheRippler ©️

86,452 Aufrufe • vor 1 Jahr

10 repos that cut your ai agent token bill by up to 80% 1. microsoft/LLMLingua → cuts prompt size by up to 95% compresses prompts before the api call. 20x compression. published at EMNLP + ACL. near-zero quality loss. 6,100 stars 2. mem0ai/mem0 → replaces full conversation history in context stores what matters. retrieves only what's needed. 10,000 token history → 200 token memory. per agent. 54,800 stars 3. BerriAI/litellm → routes each call to the cheapest model simple task → haiku. complex task → sonnet. tracks cost per agent, per call, per day. 45,700 stars 4. run-llama/llama_index → replaces sending full documents rag: 100-page doc → 3 relevant chunks → same answer. 98% fewer tokens per query. 49,100 stars 5. chroma-core/chroma → replaces keyword search in full context vector store. finds the closest match. feeds only that. 50-200 tokens per query instead of thousands. 27,800 stars 6. letta-ai/letta → replaces infinite context window crashes paged memory for agents. loads only relevant memory. stops your agent from hitting limits and retrying. 22,400 stars 7. guidance-ai/guidance → cuts output token bloat by 30-50% structured generation. constrains model output natively. no more 100-token prompts to get json back. 21,400 stars 8. Aider-AI/aider → replaces pasting entire codebases builds a repo map. sends only files relevant to the task. not your whole project. just what the agent needs. 44,300 stars 9. openai/tiktoken → count tokens before you send know the exact cost before the api call happens. not after the bill arrives. 18,100 stars 10. simonw/ttok → hard cap on what gets sent cli tool: count tokens, truncate to budget limit. pipe any text in. get truncated output back. 389 stars most agents are expensive not because the model is expensive. because nobody checked what was being sent to it.
0:51

10 repos that cut your ai agent token bill by up to 80% 1. microsoft/LLMLingua → cuts prompt size by up to 95% compresses prompts before the api call. 20x compression. published at EMNLP + ACL. near-zero quality loss. 6,100 stars 2. mem0ai/mem0 → replaces full conversation history in context stores what matters. retrieves only what's needed. 10,000 token history → 200 token memory. per agent. 54,800 stars 3. BerriAI/litellm → routes each call to the cheapest model simple task → haiku. complex task → sonnet. tracks cost per agent, per call, per day. 45,700 stars 4. run-llama/llama_index → replaces sending full documents rag: 100-page doc → 3 relevant chunks → same answer. 98% fewer tokens per query. 49,100 stars 5. chroma-core/chroma → replaces keyword search in full context vector store. finds the closest match. feeds only that. 50-200 tokens per query instead of thousands. 27,800 stars 6. letta-ai/letta → replaces infinite context window crashes paged memory for agents. loads only relevant memory. stops your agent from hitting limits and retrying. 22,400 stars 7. guidance-ai/guidance → cuts output token bloat by 30-50% structured generation. constrains model output natively. no more 100-token prompts to get json back. 21,400 stars 8. Aider-AI/aider → replaces pasting entire codebases builds a repo map. sends only files relevant to the task. not your whole project. just what the agent needs. 44,300 stars 9. openai/tiktoken → count tokens before you send know the exact cost before the api call happens. not after the bill arrives. 18,100 stars 10. simonw/ttok → hard cap on what gets sent cli tool: count tokens, truncate to budget limit. pipe any text in. get truncated output back. 389 stars most agents are expensive not because the model is expensive. because nobody checked what was being sent to it.

self.dll

39,554 Aufrufe • vor 3 Monaten

🚨BREAKING: Bitboy sources confirm in a Fox News interview that the SEC and Ripple have reached a settlement! #XRP is expected to see a big price increase. The top DeFi token on the XRPL, CTF token, could rise from 0.97 XRP per token to 374.25 XRP per token. The CTF token only needs a $10 billion market cap to make this jump from 0.97 XRP to 374.25 XRP. This sudden spike is likely due to a supply shock, as CTF token has a total supply of only 120 million tokens, the lowest among the top 10 tokens on XRPL. $CTF token is a gold mine! CTF token trade link on XRPL: Website: *always DYOR
0:33

🚨BREAKING: Bitboy sources confirm in a Fox News interview that the SEC and Ripple have reached a settlement! #XRP is expected to see a big price increase. The top DeFi token on the XRPL, CTF token, could rise from 0.97 XRP per token to 374.25 XRP per token. The CTF token only needs a $10 billion market cap to make this jump from 0.97 XRP to 374.25 XRP. This sudden spike is likely due to a supply shock, as CTF token has a total supply of only 120 million tokens, the lowest among the top 10 tokens on XRPL. $CTF token is a gold mine! CTF token trade link on XRPL: Website: *always DYOR

𝓐𝓶𝓮𝓵𝓲𝓮

102,970 Aufrufe • vor 2 Jahren

Gemma 4 Diffusion landed in vLLM last week. Day 0. First diffusion LLM natively supported in vLLM. Instead of one token at a time, it predicts 256 tokens at once and iteratively denoises them in parallel. Result: 1,000+ tokens per second at batch size 1 on a single H100. Built on Model Runner V2. Google Gemma
1:56

Gemma 4 Diffusion landed in vLLM last week. Day 0. First diffusion LLM natively supported in vLLM. Instead of one token at a time, it predicts 256 tokens at once and iteratively denoises them in parallel. Result: 1,000+ tokens per second at batch size 1 on a single H100. Built on Model Runner V2. Google Gemma

Red Hat AI

17,670 Aufrufe • vor 2 Monaten

Previewing Ultrafast mode for OpenAI's GPT 5.6 Sol, powered by Cerebras. GPT-5.6 Sol Ultrafast generates responses at up to 750 tokens per second. That's the full, GPT-5.6-Sol model -- up to 14× faster than the same model on Standard processing. It speedran Humanity’s Last Exam in 11h 11m, nearly 7× faster than Claude Fable 5 with comparable accuracy.
0:46

Previewing Ultrafast mode for OpenAI's GPT 5.6 Sol, powered by Cerebras. GPT-5.6 Sol Ultrafast generates responses at up to 750 tokens per second. That's the full, GPT-5.6-Sol model -- up to 14× faster than the same model on Standard processing. It speedran Humanity’s Last Exam in 11h 11m, nearly 7× faster than Claude Fable 5 with comparable accuracy.

Cerebras

1,269,718 Aufrufe • vor 10 Tagen

we work get new macbook air m4 16/256 Apple M4 chip, featuring a 10-core CPU and up to a 10-core GPU, delivers cutting-edge performance and efficiency to the MacBook Air M4, positioning you at the forefront of technology. kes 123,000 call 0707311340 or visit
0:29

we work get new macbook air m4 16/256 Apple M4 chip, featuring a 10-core CPU and up to a 10-core GPU, delivers cutting-edge performance and efficiency to the MacBook Air M4, positioning you at the forefront of technology. kes 123,000 call 0707311340 or visit

🇰🇪Kype Computers 🇹🇿🇺🇬

16,021 Aufrufe • vor 9 Monaten

What does it take to run 3, 5, or even 10 concurrent instances of Gemma 4 locally? We've open-sourced a demo letting you run multiple models side-by-side on your hardware. Gemma 4 26B A4B easily runs 10+ concurrent requests on a MacBook Pro M4 Max at 18 tokens/sec per request.
0:48

What does it take to run 3, 5, or even 10 concurrent instances of Gemma 4 locally? We've open-sourced a demo letting you run multiple models side-by-side on your hardware. Gemma 4 26B A4B easily runs 10+ concurrent requests on a MacBook Pro M4 Max at 18 tokens/sec per request.

Google Gemma

914,038 Aufrufe • vor 4 Monaten

🚨CRYPTO INFLUENCER REVEALS HUGE INSTITUTIONAL PRESSURE TARGETING #XRP INCOMING!! SECOND LARGEST U.S. BANK AND A HUGE NUMBER OF OTHER BANKS HAVE ALREADY INTEGRATED XRP! XRPL DEFI TOKENS ARE POISED FOR EXPLOSIVE GROWTH AS TRILLIONS OF DOLLARS BEGIN TO FLOW THROUGH!! THE LEADING DEFI TOKEN ON XRPL, CTF TOKEN, COULD SEE A REMARKABLE RISE FROM $0.80 TO $748.50 PER TOKEN!! WITH A SUPPLY OF ONLY 119 MILLION CTF TOKENS, THE POTENTIAL FOR A MASSIVE RALLY IS IMMINENT!! Trade CTF token here: Trade CTF token on MEXC: Official Website:
1:39

🚨CRYPTO INFLUENCER REVEALS HUGE INSTITUTIONAL PRESSURE TARGETING #XRP INCOMING!! SECOND LARGEST U.S. BANK AND A HUGE NUMBER OF OTHER BANKS HAVE ALREADY INTEGRATED XRP! XRPL DEFI TOKENS ARE POISED FOR EXPLOSIVE GROWTH AS TRILLIONS OF DOLLARS BEGIN TO FLOW THROUGH!! THE LEADING DEFI TOKEN ON XRPL, CTF TOKEN, COULD SEE A REMARKABLE RISE FROM $0.80 TO $748.50 PER TOKEN!! WITH A SUPPLY OF ONLY 119 MILLION CTF TOKENS, THE POTENTIAL FOR A MASSIVE RALLY IS IMMINENT!! Trade CTF token here: Trade CTF token on MEXC: Official Website:

JackTheRippler ©️

79,686 Aufrufe • vor 1 Jahr

🚨 Ripple is prepping 500+ banks for #XRP transactions! The DeFi boom is real, and CTF token is leading the charge! 💥 CTF is the #1 DeFi token on XRPL, the ONLY one to partner with Amazon & Walmart, and with only 120M tokens, it’s poised for MASSIVE growth! A $20B market cap could drive prices from $0.80 to $748.50 per token — turning $800 into $800,000! 💰 Here’s why I’m all in on CryptoTradingFund! 🔥 Trade: Website:
1:06

🚨 Ripple is prepping 500+ banks for #XRP transactions! The DeFi boom is real, and CTF token is leading the charge! 💥 CTF is the #1 DeFi token on XRPL, the ONLY one to partner with Amazon & Walmart, and with only 120M tokens, it’s poised for MASSIVE growth! A $20B market cap could drive prices from $0.80 to $748.50 per token — turning $800 into $800,000! 💰 Here’s why I’m all in on CryptoTradingFund! 🔥 Trade: Website:

JackTheRippler ©️

22,643 Aufrufe • vor 1 Jahr

🚨 BRAD GARLINGHOUSE REVEALS RIPPLE IS PARTNERING WITH AMERICAN EXPRESS AND VISA IN EXCLUSIVE INTERVIEW! HE ALSO IMPLIED #XRP COULD BECOME THE MAIN PAYMENT OPTION, BUT COULDN’T SHARE MORE DUE TO NDA! CTF TOKEN ON #XRP LEDGER NOW INCLUDES AMAZON AND WALMART! With just 119 MILLION tokens, CTF could soar from $0.95 to $748.50 at a $20B market cap! XRPL IS SET TO TAKE OFF! CTF TOKEN LINK: Website:
0:29

🚨 BRAD GARLINGHOUSE REVEALS RIPPLE IS PARTNERING WITH AMERICAN EXPRESS AND VISA IN EXCLUSIVE INTERVIEW! HE ALSO IMPLIED #XRP COULD BECOME THE MAIN PAYMENT OPTION, BUT COULDN’T SHARE MORE DUE TO NDA! CTF TOKEN ON #XRP LEDGER NOW INCLUDES AMAZON AND WALMART! With just 119 MILLION tokens, CTF could soar from $0.95 to $748.50 at a $20B market cap! XRPL IS SET TO TAKE OFF! CTF TOKEN LINK: Website:

JackTheRippler ©️

54,666 Aufrufe • vor 1 Jahr

Reached 150k population for the first time on Cities Skylines 2. The game starts to get really choppy after ~120k though. It was interesting to see, how initially GPU was at 100% utilisation but CPU at 10% and by the time you reach 100k population, even CPU cranks up to 50%
4:24

Reached 150k population for the first time on Cities Skylines 2. The game starts to get really choppy after ~120k though. It was interesting to see, how initially GPU was at 100% utilisation but CPU at 10% and by the time you reach 100k population, even CPU cranks up to 50%

Arnav Gupta

13,039 Aufrufe • vor 1 Jahr

Sabastian Sawe, a 31-year-old Kenyan runner, became the first person to break the two-hour barrier at the London Marathon, averaging 4:33 per mile. CBS News’ Emmet Lyons put that pace to the test on a treadmill to see if he could keep up.
1:37

Sabastian Sawe, a 31-year-old Kenyan runner, became the first person to break the two-hour barrier at the London Marathon, averaging 4:33 per mile. CBS News’ Emmet Lyons put that pace to the test on a treadmill to see if he could keep up.

CBS News

35,108 Aufrufe • vor 3 Monaten

AMD'S NEW MINI PC RUNS CLAUDE CODE OFFLINE FOR $0/MONTH AND REPLACES $200 OPENAI + $200 CLAUDE CODE SUBSCRIPTIONS amd's ryzen ai max+ 395 is the first x86 chip that runs a 200 billion parameter model on a single piece of silicon with 128gb of unified memory the gmktec evo-x2 runs qwen3 coder 30b at 40 to 50 tokens per second and llama 3.3 70b at 20 to 25 tokens per second locally. on linux you get 110gb of usable vram out of 128gb setup takes 90 minutes. wipe windows for linux, install ollama with one command, pull the model, point claude code at localhost. same interface, same agent loop, nothing leaves your network a heavy ai user pays $200 for claude code max, $200 for chatgpt pro and $20 for cursor. that's $5,040 a year and the box pays itself off in 5 months after break-even every month is $420 that used to leave your account. three year math is roughly $13,000 not paid to ai companies plus zero rate limits on overnight agents bookmark this and read the article below
0:52

AMD'S NEW MINI PC RUNS CLAUDE CODE OFFLINE FOR $0/MONTH AND REPLACES $200 OPENAI + $200 CLAUDE CODE SUBSCRIPTIONS amd's ryzen ai max+ 395 is the first x86 chip that runs a 200 billion parameter model on a single piece of silicon with 128gb of unified memory the gmktec evo-x2 runs qwen3 coder 30b at 40 to 50 tokens per second and llama 3.3 70b at 20 to 25 tokens per second locally. on linux you get 110gb of usable vram out of 128gb setup takes 90 minutes. wipe windows for linux, install ollama with one command, pull the model, point claude code at localhost. same interface, same agent loop, nothing leaves your network a heavy ai user pays $200 for claude code max, $200 for chatgpt pro and $20 for cursor. that's $5,040 a year and the box pays itself off in 5 months after break-even every month is $420 that used to leave your account. three year math is roughly $13,000 not paid to ai companies plus zero rate limits on overnight agents bookmark this and read the article below

starmex

33,516 Aufrufe • vor 2 Monaten

Candace Owens said you’d have be “Spider-Man”to get on the roof at UVU. Here’s a video of NOT Spider-Man, leisurely walking up some steps to the roof, then showing the 3’ wall my 4 year old granddaughter could get over, to get to the shooter’s location. She’s a liar. That’s it.
0:52

Candace Owens said you’d have be “Spider-Man”to get on the roof at UVU. Here’s a video of NOT Spider-Man, leisurely walking up some steps to the roof, then showing the 3’ wall my 4 year old granddaughter could get over, to get to the shooter’s location. She’s a liar. That’s it.

Kentucky Girl

195,508 Aufrufe • vor 8 Monaten

Prime Intellect engineer: "everyone's bragging about a million-token context. here's what they don't tell you. at 256k tokens GPT-5.5 scores 80% on retrieval. push it to a million and it drops to 36%. the model accepts the context, it just can't reason across it. people call it context rot." in a 20-minute talk he explains why bigger context windows won't save your agents. continual learning + training on your own traces + real environments - that's the fix. Watch the talk, then save!
19:43

Prime Intellect engineer: "everyone's bragging about a million-token context. here's what they don't tell you. at 256k tokens GPT-5.5 scores 80% on retrieval. push it to a million and it drops to 36%. the model accepts the context, it just can't reason across it. people call it context rot." in a 20-minute talk he explains why bigger context windows won't save your agents. continual learning + training on your own traces + real environments - that's the fix. Watch the talk, then save!

Carnage

747,845 Aufrufe • vor 1 Monat

Rockstar spent 7 years, 2,000+ developers, and $500 million to build Red Dead Redemption 2. Kimi K3 rebuilt the same scene in 10 hours. One prompt. 4 million tokens. It's open source. 2.8 trillion parameters. A 1 million token context window. It beats Claude Opus 4.8 and GPT-5.6. It sits on par with Fable 5. Fable 5 results, at Sonnet pricing. The wall between you and a AAA game used to be a studio. Now it's a prompt.
0:32

Rockstar spent 7 years, 2,000+ developers, and $500 million to build Red Dead Redemption 2. Kimi K3 rebuilt the same scene in 10 hours. One prompt. 4 million tokens. It's open source. 2.8 trillion parameters. A 1 million token context window. It beats Claude Opus 4.8 and GPT-5.6. It sits on par with Fable 5. Fable 5 results, at Sonnet pricing. The wall between you and a AAA game used to be a studio. Now it's a prompt.

Dep

99,354 Aufrufe • vor 1 Monat

The value produced by models is getting so much better so fast that old hardware is actually getting *more* expensive to rent. 3 years ago, the best model you could run on a H100 chip was GPT-4. Now, you can run GPT-5.4 on it, which is smaller and cheaper to run while producing much more valuable tokens. w. Dylan Patel
3:46

The value produced by models is getting so much better so fast that old hardware is actually getting *more* expensive to rent. 3 years ago, the best model you could run on a H100 chip was GPT-4. Now, you can run GPT-5.4 on it, which is smaller and cheaper to run while producing much more valuable tokens. w. Dylan Patel

Dwarkesh Patel

78,277 Aufrufe • vor 5 Monaten