Fara-7B: An efficient agentic model for computer use
1–10 of 92 posts
Re: Fara-7B: An efficient agentic model for computer use
#2Are there any agentic models like this that would work for controlling input in arbitrary video games? I've been wanting to have an AI play Kerbal Space Program because I think it would just be pretty hilarious.
Re: Fara-7B: An efficient agentic model for computer use
#3* fine tuned Qwen-7B
Re: Fara-7B: An efficient agentic model for computer use
#4How much VRAM would this require, if I would want to run this locally?
I bought a 12GB Nvidia card a year ago. In general I'm having a hard time to find the actual required hardware specs for any self hosted AI model. Any tips/suggestions/recommended resources for that?
Re: Fara-7B: An efficient agentic model for computer use
#5How much VRAM would this require, if I would want to run this locally? I bought a 12GB Nvidia card a year ago. In general I'm having a hard time to find the actual required hardware specs for any self hosted AI model. Any tips/suggestions/recommended resources for that?
One quick way to estimate a lower bound is to take the number of parameters and multiply it with the bits per parameter. So a model with 7 billion parameters running with float8 types would be ~7 GB to load at a minimum. The attention mechanism would require more on top of that, and depends on the size of the context window.
You'll also need to load inputs (images in this case) onto the GPU memory, and that depends on the image resolution and batch size.
Re: Fara-7B: An efficient agentic model for computer use
#6* fine tuned Qwen-7B
So.. the tables are really turning?
Re: Fara-7B: An efficient agentic model for computer use
#7Are there any agentic models like this that would work for controlling input in arbitrary video games? I've been wanting to have an AI play Kerbal Space Program because I think it would just be pretty hilarious.
I might suggest looking at Alibaba's open source AgentEvolver. It doesn't specifically target video games, but it's an agentic system designed around a more OODA loop evolutionary system than the kind of train/inference system, has potential, could be exciting to see.
I like how they classifythr sub problems of their work. Environment/ self questioning -> task / self questioning -> trajectory / self evaluation. OODA-esque.
https://arxiv.org/abs/2511.10395 https://github.com/modelscope/AgentEvolver with thanks to Sung Kim who has been a great feed https://bsky.app/profile/sungkim.bsky.social/post/3m5xkgttk3...
Re: Fara-7B: An efficient agentic model for computer use
#8Are there any agentic models like this that would work for controlling input in arbitrary video games? I've been wanting to have an AI play Kerbal Space Program because I think it would just be pretty hilarious.
https://deepmind.google/blog/sima-2-an-agent-that-plays-reas...
(not a local model)
Re: Fara-7B: An efficient agentic model for computer use
#9Are there any agentic models like this that would work for controlling input in arbitrary video games? I've been wanting to have an AI play Kerbal Space Program because I think it would just be pretty hilarious.
i'm curious what would happen if you got it to play online poker...
Re: Fara-7B: An efficient agentic model for computer use
#10How much VRAM would this require, if I would want to run this locally? I bought a 12GB Nvidia card a year ago. In general I'm having a hard time to find the actual required hardware specs for any self hosted AI model. Any tips/suggestions/recommended resources for that?
I use LMStudio for running models locally (macOS) and it tries to estimate whether the model would fit in my GPU memory (which is the same thing as main memory for Macs).
The Q4_K_S quantized version of Microsoft Fara 7B is a 5.8GB download. I'm pretty sure it would work on a 12GB Nvidia card. Even the Q8 one (9.5GB) could work.