Загрузка видео...
Не удалось загрузить видео
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 просмотров • 1 год назад •via X (Twitter)
Комментарии: 11

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

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

luis1 год назад
🙂↔️🤯

GawdOfAi1 год назад
why not use mlx?

Vaibhav (VB) Srivastav1 год назад
why not use both :)

Ankush Singal1 год назад
just added here:

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

Muhamad1 год назад
Can it handle audio input and output?

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

Anda1 год назад
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 год назад
Have you tried SFT with audio/video with it?
