Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Fara-7B: An efficient agentic model for computer use

github.com

Post reply on HN
Print view View original

11–20 of 92 posts

Re: Fara-7B: An efficient agentic model for computer use

#11

Post by daemonologist »

maartenh wrote: post #4

How 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?

12GB will be sufficient to run a quantized version, provided you're not running anything else memory-hungry on the GPU.

You're not finding hardware specs because there are a lot of variables at play - the degree to which the weights are quantized, how much space you want to set aside for the KV cache, extra memory needed for multimodal features, etc.

My rule of thumb is 1 byte per parameter to be comfortable (running a quantization with somewhere between 4.5 and 6 bits per parameter and leaving some room for the cache and extras), so 7 GB for 7 billion parameters. If you need a really large context you'll need more; if you want to push it you can get away with a little less.

Re: Fara-7B: An efficient agentic model for computer use

#12

Post by A4ET8a8uTh0_v2 »

Looking at the table, I will admit that I don't get most of the use cases ( maybe with exception of comparison shopping ( gather info ), but are people really 'outsourcing' shopping? Am I really that much outside what 'normal' consumers do these days?

Task Segment Tasks SoM GPT-4o-0513 SoM o3-mini SoM GPT-4o GLM-4.1V-9B OAI Comp-Use UI-TARS-1.5 Fara-7B Single-Site Tasks Shopping 56 62.5 71.4 38.1 31.0 42.3 41.1 52.4 Flights 51 60.1 39.2 11.1 10.5 17.6 10.5 37.9 Hotels 52 68.6 56.4 31.4 19.9 26.9 35.3 53.8 Restaurants 52 67.9 59.6 47.4 32.1 35.9 22.4 47.4 Activities 80 70.4 62.9 41.7 26.3 30.4 9.6 36.3 Ticketing 57 58.5 56.7 37.4 35.7 49.7 30.4 38.6 Real Estate 48 34.0 17.4 20.1 16.0 9.0 9.7 23.6 Jobs/Careers 50 49.3 44.0 32.7 22.7 20.7 20.7 28.0 Multi-Step Tasks Shopping List (2 items) 51 66.0 62.7 17.0 7.8 34.0 20.9 49.0 Comparison Shopping 57 67.3 59.1 27.5 22.8 1.2 8.8 32.7 Compositional Tasks 55 51.5 39.4 26.7 17.0 10.3 9.1 23.0 Overall

Re: Fara-7B: An efficient agentic model for computer use

#14

Post by pogue »

Why does Microsoft keep releasing models trained on synthetic data? Is it possible their contract with OpenAI won't let them do anything else?

I would think Microsoft, of all companies, would want to be working on their own LLM behind the scenes, even if they're relying on OpenAI for the bulk of their work.

Meta seems to be the only US company releasing big 'open source' models, while Chinese companies continue to release many completely open source LLMs.

Re: Fara-7B: An efficient agentic model for computer use

#16

Post by hsaliak »

ghrjfjfnnfn wrote: post #15

Forgive me if I can't keep up with the latest AI bubble mania buzzwords, but what is "agentic" even supposed to mean? As far as I can tell it doesn't have a precise definition, and doesn't even sound like proper English.

it means you can make it do stuff (run preconfigured programs) for you, and not just chat with you

Re: Fara-7B: An efficient agentic model for computer use

#18

Post by doug_durham »

A4ET8a8uTh0_v2 wrote: post #12

Looking at the table, I will admit that I don't get most of the use cases ( maybe with exception of comparison shopping ( gather info ), but are people really 'outsourcing' shopping? Am I really that much outside what 'normal' consumers do these days? Task Segment Tasks SoM GPT-4o-0513 SoM o3-mini SoM GPT-4o GLM-4.1V-9B OAI Comp-Use UI-TARS-1.5 Fara-7B Single-Site Tasks Shopping 56 62.5 71.4 38.1 31.0 42.3 41.1 52.4…

I can't imagine having an AI agent book anything our purchase anything in the same way that I wouldn't have someone I don't know personally do that for me. It should do the research and take me to the place where I need to take over.

Re: Fara-7B: An efficient agentic model for computer use

#19

Post by doug_durham »

ghrjfjfnnfn wrote: post #15

Forgive me if I can't keep up with the latest AI bubble mania buzzwords, but what is "agentic" even supposed to mean? As far as I can tell it doesn't have a precise definition, and doesn't even sound like proper English.

Ask your favorite LLM. It will tell you.

Re: Fara-7B: An efficient agentic model for computer use

#20

Post by dwohnitmok »

ghrjfjfnnfn wrote: post #15

Forgive me if I can't keep up with the latest AI bubble mania buzzwords, but what is "agentic" even supposed to mean? As far as I can tell it doesn't have a precise definition, and doesn't even sound like proper English.

"Agentic" doesn't really mean much and I dislike it. There's no clean line between a "normal" LLM and an "agentic" LLM. Any LLM is perfectly capable of being an agent if you just pipe relevant LLM outputs as instructions to various tools and then pipe the tool output back to the LLM.

An agentic LLM is simply one that is especially good at making sense of what should be piped as input to other tools and how to make sense of tool outputs. Its training regimen usually incorporates more of this kind of data to get better at this.

Post reply on HN