Home / AI GPUs / NVIDIA RTX 3090 Ti 24 GB

NVIDIA · GeForce

NVIDIA RTX 3090 Ti 24 GB

24 GB GDDR6X advertised VRAM. Usable memory for calculations is 90% of advertised capacity. This page is the chip + VRAM entity — not a single cooler SKU.

Models that fit (calculated)

ModelParamsQ4Q8FP16Max context in VRAM
Qwen2.5 0.5B Instruct494MFitsFitsFits32K
TinyLlama 1.1B Chat v1.01.1BFitsFitsFits2K
Llama 3.2 1B Instruct1.2BFitsFitsFits128K
Qwen2.5 1.5B Instruct1.5BFitsFitsFits32K
Qwen2.5-Coder 1.5B Instruct1.5BFitsFitsFits32K
SmolLM2 1.7B Instruct1.7BFitsFitsFits8K
Gemma 2 2B Instruct2.6BFitsFitsFits8K
Qwen2.5 3B Instruct3.1BFitsFitsFits32K
Llama 3.2 3B Instruct3.2BFitsFitsFits128K
Phi-3.5 Mini Instruct3.8BFitsFitsFits32K
Phi-3 Mini 128K Instruct3.8BFitsFitsFits32K
Phi-3 Mini 4K Instruct3.8BFitsFitsFits4K
Phi-4 Mini Instruct3.8BFitsFitsFits128K
Code Llama 7B Instruct6.7BFitsFitsFits16K
Vicuna 7B v1.56.7BFitsFitsFits4K
DeepSeek LLM 7B Chat6.9BFitsFitsFits4K
StarCoder2 7B7.2BFitsFitsFits16K
Falcon 7B Instruct7.2BFitsFitsFits16K
OpenChat 3.5 7B7.2BFitsFitsFits8K
Mistral 7B Instruct v0.37.3BFitsFitsFits32K
OLMo 2 7B Instruct7.3BFitsFitsFits4K
Falcon 3 7B Instruct7.5BFitsFitsFits32K
DeepSeek R1 Distill Qwen 7B7.6BFitsFitsFits128K
Qwen2.5 7B Instruct7.6BFitsFitsFits32K
Qwen2.5-Coder 7B Instruct7.6BFitsFitsFits32K
Qwen2.5-Math 7B Instruct7.6BFitsFitsFits4K
Qwen2 7B Instruct7.6BFitsFitsFits32K
DeepSeek R1 Distill Llama 8B8.0BFitsFitsFits128K
Hermes 3 Llama 3.1 8B8.0BFitsFitsFits128K
Llama 3.1 8B Instruct8.0BFitsFitsFits128K
Llama 3 8B Instruct8.0BFitsFitsFits8K
Qwen3 8B8.2BFitsFitsFits40K
Yi 1.5 9B Chat8.8BFitsFitsFits4K
Gemma 2 9B Instruct9.2BFitsFitsFits8K
GLM-4-9B-04149.4BFitsFitsFits32K
GLM-4 9B Chat9.4BFitsFitsFits16K
Falcon 3 10B Instruct10BFitsFitsOffload32K
SOLAR 10.7B Instruct11BFitsFitsOffload4K
Mistral Nemo 12B Instruct12BFitsFitsOffload64K
Code Llama 13B Instruct13BFitsFitsOffload16K
Vicuna 13B v1.513BFitsFitsOffload4K
OLMo 2 13B Instruct14BFitsFitsOffload4K
Phi-3 Medium 128K Instruct14BFitsFitsOffload64K
Phi-3 Medium 4K Instruct14BFitsFitsOffload4K
DeepSeek R1 Distill Qwen 14B15BFitsFitsOffload64K
Phi-415BFitsFitsOffload16K
Qwen2.5 14B Instruct15BFitsFitsOffload32K
Qwen3 14B15BFitsFitsOffload40K
StarCoder2 15B16BFitsFitsOffload16K
GPT-OSS 20B22BFitsOffloadOffload128K
Mistral Small 24B Instruct24BFitsOffloadOffload32K
Gemma 2 27B Instruct27BFitsOffloadOffload8K
DeepSeek R1 Distill Qwen 32B33BOffloadOffloadNo16K
Qwen2.5 32B Instruct33BOffloadOffloadNo16K
Qwen2.5-Coder 32B Instruct33BOffloadOffloadNo16K
QwQ 32B33BOffloadOffloadNo16K
Qwen3 32B33BOffloadOffloadNo16K
Code Llama 34B Instruct34BOffloadOffloadNo16K
Yi 1.5 34B Chat34BOffloadOffloadNo4K
Mixtral 8x7B Instruct47BOffloadOffloadNo—
DeepSeek R1 Distill Llama 70B71BOffloadNoNo—
Hermes 3 Llama 3.1 70B71BOffloadNoNo—
Llama 3.1 70B Instruct71BOffloadNoNo—
Llama 3.3 70B Instruct71BOffloadNoNo—
Qwen2.5 72B Instruct73BOffloadNoNo—
GPT-OSS 120B117BNoNoNo—
Mixtral 8x22B Instruct141BNoNoNo—

Available graphics cards

These are Icecat product SKUs mapped to this chip. Different board-partner cards are not assumed to share a price. Amazon CTAs appear only for EXACT/HIGH matches that are not bundled accessories.

MSI

MSI SUPRIM GeForce RTX 3090 Ti X 24G NVIDIA 24 GB GDDR6X

24 GB · Amazon EXACT

$2210.00

Check price on Amazon
MSI

MSI GAMING GeForce RTX 3090 Ti X TRIO 24GB NVIDIA GDDR6X

24 GB · Amazon unmatched

Check availability
ASUS

ASUS TUF Gaming TUF-RTX3090TI-O24G-GAMING NVIDIA GeForce RTX 3090 Ti 24 GB GDDR6X

24 GB · Amazon unmatched

Check availability
ASUS

ASUS TUF Gaming TUF-RTX3090TI-24G-GAMING NVIDIA GeForce RTX 3090 Ti 24 GB GDDR6X

24 GB · Amazon unmatched

Check availability
ASUS

ASUS ROG -STRIX-LC-RTX3090TI-O24G-GAMING NVIDIA GeForce RTX 3090 Ti 24 GB GDDR6X

24 GB · Amazon unmatched

Check availability

Find a GPU for a specific AI model

Sources

GPU identity and VRAM: Icecat structured specifications. Compatibility: RigForAI calculated estimate. Amazon: live affiliate match on individual SKUs, via /go/amazon/.