NVIDIA GeForce RTX 3090 Ti — Local LLM Performance & Compatibility

Written by Jakub Rusinowski · Last updated September 19, 2026

The fastest Ampere consumer card: 24 GB at 1,008 GB/s, matching the RTX 4090's bandwidth over the same capacity. Bought used it is one of the cheapest routes to 24 GB, at the cost of a 450 W board and no FP8.

Technical Specifications

VRAM24 GB
Memory Bandwidth1008 GB/s
TDP450 W
ArchitectureAmpere GA102
Release Year2022
MSRP at Launch$1,999
Inference Speed (Llama 3.1 8B Q4_K_M)63–122 tok/s (estimated)
Inference Speed (Llama 3.3 70B Q4_K_M)Does not fit — needs ~44 GB of 24 GB usable
Buy This HardwareAMD Radeon RX 7900 XTX 24GB — 24 GB VRAM · 355 W board powerDeploy in the Cloud NowRTX 4090 on RunPod — from $0.34/hr · rate checked 2026-07

or compare on Vast.ai from $0.35/hr (typical low · varies)

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

LLMs Compatible with 24 GB VRAM

All models below run comfortably in 24 GB VRAM with Q4_K_M quantization.

Command R FamilyCommand R (35B) · 22 GB VRAM · Q4_K_M · ollama run command-r
Qwen 3.5Qwen 3.5 35B-A3B · 22 GB VRAM · Q4_K_M · ollama run qwen3.5:35b-a3b
Qwen 3.6Qwen 3.6 35B-A3B · 22 GB VRAM · Q4_K_M · ollama run qwen3.6:35b-a3b
Nex-N2Nex-N2 mini · 22 GB VRAM · Q4_K_M · nex-n2
Yi 1.5 FamilyYi 1.5 34B Chat · 22 GB VRAM · Q4_K_M · ollama run yi:34b
Qwen 3Qwen 3 32B · 21 GB VRAM · Q4_K_M · ollama run qwen3:32b
Aya ExpanseAya Expanse 32B · 20 GB VRAM · Q4_K_M · ollama run aya-expanse:32b
DeepSeek R1DeepSeek R1 Distill Qwen 32B · 20 GB VRAM · Q4_K_M · ollama run deepseek-r1:32b

56 more families also fit 24 GB — browse the full model library.

Best Use Cases

FAQ

Can the NVIDIA GeForce RTX 3090 Ti run local LLMs?

Yes — the NVIDIA GeForce RTX 3090 Ti has 24 GB VRAM and runs The fastest Ampere consumer card: 24 GB at 1,008 GB/s, matching the RTX 4090's bandwidth over the same capacity. Bought

How fast is the NVIDIA GeForce RTX 3090 Ti for AI inference?

The NVIDIA GeForce RTX 3090 Ti is estimated to run Llama 3.1 8B at 63–122 tok/s with Q4_K_M quantization. Llama 3.3 70B does not fit: it needs about 44 GB against 24 GB usable. These are modelled estimates, not measurements — see /en/methodology.

What LLMs can I run on 24 GB VRAM?

With 24 GB you can run: Command R Family, Qwen 3.5, Qwen 3.6, Nex-N2, Yi 1.5 Family. Use Ollama for the easiest setup: ollama run llama3.1:8b.

Compare Similar GPUs

VRAM Tier

Buying Guide

← All GPU Reviews | All Hardware | Check Your Hardware | Full Benchmarks | Can I Run It?