Video yükleniyor...
Video Yüklenemedi
Running Phi 4 Mini Instruct at 75 tok/sec locally on a Mac - powered by llama.cpp! 🔥 All you need is: brew install llama.cpp Followed by: llama-cli -hf bartowski/microsoft_Phi-4-mini-instruct-GGUF:Q8_0 That's it! 🤗
30,964 görüntüleme • 1 yıl önce •via X (Twitter)
11 Yorum

Vaibhav (VB) Srivastav1 yıl önce
All thanks to @ggerganov for llama.cpp & @bartowski1182 for the quants:

glueckkanja4 yıl önce
Are you searching for a simple way to deploy device certificates with #Intune? Check out SCEPman at

luis1 yıl önce
🙂↔️🤯

GawdOfAi1 yıl önce
why not use mlx?

Vaibhav (VB) Srivastav1 yıl önce
why not use both :)

Ankush Singal1 yıl önce
just added here:

Carlos (EUR/BCN)1 yıl önce
...and when for @ollama? Is it a different architecture?

Muhamad1 yıl önce
Can it handle audio input and output?

Hüseyin1 yıl önce
Hello, which is the best model with decompilation capability for assembly c translation?

Anda1 yıl önce
That's some seriously smooth local inference speed—Phi 4 Mini's performance on llama.cpp is like watching a panda gracefully munch bamboo at hyper-speed! 🐼💨

bryan pratte1 yıl önce
Have you tried SFT with audio/video with it?
