Loading AI researcher setups...

Loading content...

ThePrimeagen AI Computer Setup - 1x RTX 4090 Specs

Quick Answer: ThePrimeagen runs a RTX 4090 (24GB VRAM total) configuration for software engineering & performance. This setup handles google/gemma-2-9b-it at 48 tokens/sec optimized for 7B-13B models.

ThePrimeagen AI Computer Setup

650K followers

Specs & Performance

24GB VRAM • 48 tok/s on 70BVerified 12/25/2025

$3,577

Total Cost

Twitter GitHub

Complete Hardware Specs

All components with current pricing and affiliate purchase links

Component	Product	Price	Purchase
GPU	RTX 4090 For streaming and AI experiments	$1,599	View on Amazon
CPU	AMD Ryzen 9 7950X 16-core for streaming + coding	$549	View on Amazon
MOTHERBOARD	Gigabyte X670E AORUS Master High-end X670E with great VRMs	$480	View on Amazon

ThePrimeagen's AI Computer Performance

LLM inference speed for models with 20+ tok/s on this 24GB VRAM setup

Model	Quantization	Tokens/sec	VRAM Used
google/gemma-2-9b-it	FP16	48 tok/s	20GB
nvidia/NVIDIA-Nemotron-Nano-9B-v2	FP16	52 tok/s	19GB
EssentialAI/rnj-1	FP16	55 tok/s	19GB
NousResearch/Hermes-3-Llama-3.1-8B	FP16	54 tok/s	17GB
meta-llama/Llama-3.1-8B-Instruct	FP16	50 tok/s	17GB
NousResearch/Meta-Llama-3.1-8B-Instruct	FP16	75 tok/s	17GB
meta-llama/Llama-Guard-3-8B	FP16	74 tok/s	17GB
meta-llama/Llama-3.1-8B-Instruct	FP16	74 tok/s	17GB
lmstudio-community/DeepSeek-R1-0528-Qwen3-8B-MLX-4bit	FP16	72 tok/s	17GB
deepseek-ai/DeepSeek-R1-Distill-Llama-8B	FP16	71 tok/s	17GB

VRAM Requirements & Usage

What this 24GB configuration can and cannot run

✅ What this setup can do

✓Run Llama 70B Q4 (needs 40GB)
✓Fine-tune 13B models with QLoRA
✓Serve multiple 7B models in parallel
✓Train custom models up to 6B parameters
✓Fast Stable Diffusion XL generation

❌ What it can't do

✗Run Llama 405B (needs 200GB+ VRAM)
✗Full fine-tuning of 70B models (needs A100/H100)
✗Multi-GPU training on 100B+ models

Total VRAM:24GB

Usable for single model:22GB (after OS overhead)

Verified Sources

All specs compiled from public sources

TWEET
Primeagen discusses local AI testing setup
January 15, 2024
VIDEO
ThePrimeagen desk and setup tour
August 20, 2023

Disclaimer: Setup compiled from public sources. Not endorsed by ThePrimeagen. All affiliate links clearly marked.

Frequently Asked Questions

Can this setup run Llama 3 70B?

No. This setup has 24GB VRAM but Llama 70B needs 40GB minimum. It can run Llama 13B and smaller models.

How much does it cost to build a similar rig?

$3,577 total. Budget alternatives: Single RTX 4090 (~$4,200) or RTX 4080 (~$2,400) for smaller models.

What models can't this run?

Llama 405B and similar 400B+ models need 200GB+ VRAM (requires 8x A100 or H100 GPUs). This 24GB setup handles up to 70B models.

Similar AI Setups

Other workstations and builds you might find interesting

PewDiePie

2x RTX 4000 Ada 20GB • $39,500 total

View setup →

MKBHD

2x RTX 4090 • $11,197 total

View setup →

Linus Tech Tips

4x RTX 4090 • $25,295 total

View setup →