Загрузка видео...

Не удалось загрузить видео

На главную

DeepSeek-R1 on Mac Studio 192GB 🪄

ggerganov's profile picture

Georgi Gerganov

59,308 subscribers

259,545 просмотров • 1 год назад •via X (Twitter)

Наука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 12

Фото профиля Georgi Gerganov
Georgi Gerganov1 год назад

The model is quantized by @UnslothAI

Фото профиля Solar Heavy
Solar Heavy1 год назад

- Moonlight

Фото профиля Unsloth AI
Unsloth AI1 год назад

Looks soo good! 🎇🐋

Фото профиля Daniel Nakov
Daniel Nakov1 год назад

come on apple, new studio

Фото профиля Georgi Gerganov
Georgi Gerganov1 год назад

M4 studio with 256GB would be the final boss

Фото профиля unfazed.
unfazed.1 год назад

@JudeSkrr il a encore drop

Фото профиля Vasilii Kharitonov 🌍
Vasilii Kharitonov 🌍1 год назад

Tried R1 32B 8bit on M4 Pro with 48 GB memory (ggml-org/DeepSeek-R1-Distill-Qwen-32B-Q8_0-GGUF), seems to run great 👍 Memory usage is 43.3/48.0GB, eval time is about 7 tokens per second.

Фото профиля GP
GP1 год назад

I need your cli setup 😏

Фото профиля Woody Lu
Woody Lu1 год назад

Could you share the noise level (in DB) of the mac when running it locally?

Фото профиля Georgi Gerganov
Georgi Gerganov1 год назад

Not sure how to measure it. It only makes noise for very long contexts, otherwise it's completely silent. And when it makes noise, it's not really loud IMO.

Фото профиля Alexander Kvamme
Alexander Kvamme1 год назад

What profiling tool are you using? Much cleaner than htop

Фото профиля Georgi Gerganov
Georgi Gerganov1 год назад

asitop

Похожие видео

we just added an early preview of DeepSeek-R1 to the fullmoon TestFlight you can use it on iPhone, iPad, Mac, and Vision
0:20

we just added an early preview of DeepSeek-R1 to the fullmoon TestFlight you can use it on iPhone, iPad, Mac, and Vision

Jordan Singer

52,763 просмотров • 1 год назад

DeepSeek R1 + FactSet = Financial Research on Steroids
0:34

DeepSeek R1 + FactSet = Financial Research on Steroids

Aravind Srinivas

582,161 просмотров • 1 год назад

deepseek-r1-distill-llama-70b on groq
0:50

deepseek-r1-distill-llama-70b on groq

Developers Digest

143,277 просмотров • 1 год назад

DeepSeek R1 is now active on FluxAI.
0:49

DeepSeek R1 is now active on FluxAI.

Daniel Keller

23,528 просмотров • 1 год назад

OpenAI's nightmare: DeepSeek R1 on a Raspberry Pi
4:17

OpenAI's nightmare: DeepSeek R1 on a Raspberry Pi

Jeff Geerling

23,725 просмотров • 1 год назад

o3-mini-high (left) vs. deepseek-r1 (right) results from the first try deepseek-r1 is cracked... wtf!
0:30

o3-mini-high (left) vs. deepseek-r1 (right) results from the first try deepseek-r1 is cracked... wtf!

elvis

719,763 просмотров • 1 год назад

Watch DeepSeek-R1 (8B) "think" in realtime on a regular computer.
1:43

Watch DeepSeek-R1 (8B) "think" in realtime on a regular computer.

Vincent Kennedy

43,351 просмотров • 1 год назад

🚨 DeepSeek just dropped DeepSeek R1-0528 and it's INSANE for coding Built an entire game with Nebius Studio in three turn. The improvement from previous versions is wild. - API access available - Safe to use If this is R1... DeepSeek R2 is going to be absolutely nuts. How to access 👇 1/3
0:44

🚨 DeepSeek just dropped DeepSeek R1-0528 and it's INSANE for coding Built an entire game with Nebius Studio in three turn. The improvement from previous versions is wild. - API access available - Safe to use If this is R1... DeepSeek R2 is going to be absolutely nuts. How to access 👇 1/3

AshutoshShrivastava

61,058 просмотров • 1 год назад

DeepSeek R1 + Perplexity is INSANE 🤯
13:04

DeepSeek R1 + Perplexity is INSANE 🤯

Julian Goldie SEO

168,119 просмотров • 1 год назад

DeepSeek-R1 + Windsurf is INSANE! 🤯
12:13

DeepSeek-R1 + Windsurf is INSANE! 🤯

Julian Goldie SEO

46,671 просмотров • 1 год назад

Grok 4's coding skills are worse than DeepSeek-R1 (the old version, not even the newer DeepSeek-R1-0528)! 😅 #Grok4
0:54

Grok 4's coding skills are worse than DeepSeek-R1 (the old version, not even the newer DeepSeek-R1-0528)! 😅 #Grok4

ShanghaiPanda （ Account deactivation）

118,909 просмотров • 11 месяцев назад

Sarvam-M now has 8.6 lakh downloads on Hugging Face, beating DeepSeek-R1!
1:58

Sarvam-M now has 8.6 lakh downloads on Hugging Face, beating DeepSeek-R1!

Caleb

55,857 просмотров • 1 год назад

Automate Anything with DeepSeek-R1, here’s how
19:40

Automate Anything with DeepSeek-R1, here’s how

Julian Goldie SEO

880,323 просмотров • 1 год назад

Project Veritas: Make DeepSeek R1 truth seeking
0:42

Project Veritas: Make DeepSeek R1 truth seeking

Aravind Srinivas

96,555 просмотров • 1 год назад

Build anything with DeepSeek-R1, here's how...
18:30

Build anything with DeepSeek-R1, here's how...

Julian Goldie SEO

3,468,692 просмотров • 1 год назад

DeepSeek-R1 + RooCode is INSANE (FREE!) 🤯
13:19

DeepSeek-R1 + RooCode is INSANE (FREE!) 🤯

Julian Goldie SEO

48,802 просмотров • 1 год назад

DeepSeek-R1 is blowing up right now, but we're not surprised. And not just because we’ve been working closely with DeepSeek to bring these models to production. We've been betting on powerful, open-source models like DeepSeek-R1 from day one. 1/n 🧵
0:59

DeepSeek-R1 is blowing up right now, but we're not surprised. And not just because we’ve been working closely with DeepSeek to bring these models to production. We've been betting on powerful, open-source models like DeepSeek-R1 from day one. 1/n 🧵

Baseten

59,321 просмотров • 1 год назад

⚡️New "Thinking" UI with DeepSeek R1 Distilled models, running completely locally on iPhone
0:58

⚡️New "Thinking" UI with DeepSeek R1 Distilled models, running completely locally on iPhone

Private LLM

188,633 просмотров • 1 год назад

Latest Fireship video featured my run of DeepSeek R1 on M4 Mac Minis. Apple Silicon dominates in memory/bw unit economics, ideal for huge MoE models like R1 at batch_size=1 (the real-world use-case). SOTA AI may come from China, but it will run on American hardware.
0:21

Latest Fireship video featured my run of DeepSeek R1 on M4 Mac Minis. Apple Silicon dominates in memory/bw unit economics, ideal for huge MoE models like R1 at batch_size=1 (the real-world use-case). SOTA AI may come from China, but it will run on American hardware.

Alex Cheema - e/acc

79,775 просмотров • 1 год назад