Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

DeepSeek-R1 on Mac Studio 192GB 🪄

ggerganov's profile picture

Georgi Gerganov

59,308 subscribers

259,545 görüntüleme • 1 yıl önce •via X (Twitter)

Bilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

12 Yorum

Georgi Gerganov profil fotoğrafı
Georgi Gerganov1 yıl önce

The model is quantized by @UnslothAI

Solar Heavy profil fotoğrafı
Solar Heavy1 yıl önce

- Moonlight

Unsloth AI profil fotoğrafı
Unsloth AI1 yıl önce

Looks soo good! 🎇🐋

Daniel Nakov profil fotoğrafı
Daniel Nakov1 yıl önce

come on apple, new studio

Georgi Gerganov profil fotoğrafı
Georgi Gerganov1 yıl önce

M4 studio with 256GB would be the final boss

unfazed. profil fotoğrafı
unfazed.1 yıl önce

@JudeSkrr il a encore drop

Vasilii Kharitonov 🌍 profil fotoğrafı
Vasilii Kharitonov 🌍1 yıl önce

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.

GP profil fotoğrafı
GP1 yıl önce

I need your cli setup 😏

Woody Lu profil fotoğrafı
Woody Lu1 yıl önce

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

Georgi Gerganov profil fotoğrafı
Georgi Gerganov1 yıl önce

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.

Alexander Kvamme profil fotoğrafı
Alexander Kvamme1 yıl önce

What profiling tool are you using? Much cleaner than htop

Georgi Gerganov profil fotoğrafı
Georgi Gerganov1 yıl önce

asitop

Benzer Videolar

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 görüntüleme • 1 yıl önce

DeepSeek R1 is now active on FluxAI.
0:49

DeepSeek R1 is now active on FluxAI.

Daniel Keller

23,528 görüntüleme • 1 yıl önce

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

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

Developers Digest

143,277 görüntüleme • 1 yıl önce

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

DeepSeek R1 + FactSet = Financial Research on Steroids

Aravind Srinivas

582,222 görüntüleme • 1 yıl önce

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

OpenAI's nightmare: DeepSeek R1 on a Raspberry Pi

Jeff Geerling

23,725 görüntüleme • 1 yıl önce

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 görüntüleme • 1 yıl önce

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 görüntüleme • 1 yıl önce

🚨 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 görüntüleme • 1 yıl önce

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 görüntüleme • 11 ay önce

DeepSeek R1 + Perplexity is INSANE 🤯
13:04

DeepSeek R1 + Perplexity is INSANE 🤯

Julian Goldie SEO

168,119 görüntüleme • 1 yıl önce

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

DeepSeek-R1 + Windsurf is INSANE! 🤯

Julian Goldie SEO

46,671 görüntüleme • 1 yıl önce

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 görüntüleme • 1 yıl önce

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

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

Julian Goldie SEO

3,469,823 görüntüleme • 1 yıl önce

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

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

Julian Goldie SEO

48,802 görüntüleme • 1 yıl önce

Project Veritas: Make DeepSeek R1 truth seeking
0:42

Project Veritas: Make DeepSeek R1 truth seeking

Aravind Srinivas

96,555 görüntüleme • 1 yıl önce

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

Automate Anything with DeepSeek-R1, here’s how

Julian Goldie SEO

880,579 görüntüleme • 1 yıl önce

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 görüntüleme • 1 yıl önce

⚡️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 görüntüleme • 1 yıl önce

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

59,327 görüntüleme • 1 yıl önce