7 6 25

Mitko Vasilev

mitkox

AI & ML interests

Make sure you own your AI. AI in the cloud is not aligned with you; it's aligned with the company that owns it.

Recent Activity

posted an update 1 day ago

Training a model to reason in the continuous latent space based on Meta's Coconut. If it all works will apply it on the MiniCPM-o SVD-LR. Endgame is a multimodal, adaptive, and efficient foundational on device AI model.

replied to their post 10 days ago

Can it run DeepSeek V3 671B is the new 'can it run Doom'. How minimalistic can I go with on device AI with behemoth models - here I'm running DeepSeek V3 MoE on a single A6000 GPU. Not great, not terrible, for this minimalistic setup. I love the Mixture of Experts architectures. Typically I'm running my core LLM distributed over the 4 GPUs. Make sure you own your AI. AI in the cloud is not aligned with you; it's aligned with the company that owns it.

replied to their post 10 days ago

View all activity

Organizations

mitkox's activity

posted an update 1 day ago

Post

1062

Training a model to reason in the continuous latent space based on Meta's Coconut.
If it all works will apply it on the MiniCPM-o SVD-LR.
Endgame is a multimodal, adaptive, and efficient foundational on device AI model.

2 replies

replied to their post 10 days ago

DDR5 on HP Z8 G5

replied to their post 10 days ago

exactly Q2 med with ~190GB RAM

posted an update 10 days ago

Post

2394

Can it run DeepSeek V3 671B is the new 'can it run Doom'.

How minimalistic can I go with on device AI with behemoth models - here I'm running DeepSeek V3 MoE on a single A6000 GPU.

Not great, not terrible, for this minimalistic setup. I love the Mixture of Experts architectures. Typically I'm running my core LLM distributed over the 4 GPUs.

Make sure you own your AI. AI in the cloud is not aligned with you; it's aligned with the company that owns it.