Loading video...
Video Failed to Load
DeepSeek-R1 on Mac Studio 192GB 🪄
259,545 views • 1 year ago •via X (Twitter)
12 Comments

Georgi Gerganov1 year ago
The model is quantized by @UnslothAI

Solar Heavy1 year ago
- Moonlight

Unsloth AI1 year ago
Looks soo good! 🎇🐋

Daniel Nakov1 year ago
come on apple, new studio

Georgi Gerganov1 year ago
M4 studio with 256GB would be the final boss

unfazed.1 year ago
@JudeSkrr il a encore drop

Vasilii Kharitonov 🌍1 year ago
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.

GP1 year ago
I need your cli setup 😏

Woody Lu1 year ago
Could you share the noise level (in DB) of the mac when running it locally?

Georgi Gerganov1 year ago
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 Kvamme1 year ago
What profiling tool are you using? Much cleaner than htop

Georgi Gerganov1 year ago
asitop
