Skip to content
HQ
HardwareHQ
GPUsModelsCloud Pricing
HomeModels

AI Model Database

CompatibilityBrowse GPUs

299 AI models with hardware requirements, VRAM needs, and GPU compatibility data.

299models

Showing 48 of 299 matches

Large Language Models

Llama 3.1 8B

Meta

Parameters
8B
Context
128K
VRAM (Q4)
4.4GB
VRAM (FP16)
16GB
Large Language Models

Claude 3.5 Sonnet

Anthropic

Parameters
175B
Context
200K
VRAM (Q4)
96.3GB
VRAM (FP16)
350GB
Large Language Models

GPT-4o

OpenAI

Parameters
0B
Context
128K
VRAM (Q4)
—
VRAM (FP16)
—
Large Language Models

Claude Opus 4.5

Anthropic

Parameters
200B
Context
200K
VRAM (Q4)
110GB
VRAM (FP16)
400GB
Audio Models

Whisper Large v3

OpenAI

Parameters
1.55B
Context
4K
VRAM (Q4)
0.9GB
VRAM (FP16)
3.1GB
Large Language Models

Llama 4 Maverick

Meta

Parameters
400B
Context
1000K
VRAM (Q4)
220GB
VRAM (FP16)
800GB
Large Language Models

Llama 3.1 70B

Meta

Parameters
70B
Context
128K
VRAM (Q4)
38.5GB
VRAM (FP16)
140GB
Large Language Models

DeepSeek R1

DeepSeek

Parameters
671B
Context
128K
VRAM (Q4)
369.1GB
VRAM (FP16)
1342GB
Image Generation

Stable Diffusion XL 1.0

Stability AI

Parameters
6.6B
Context
4K
VRAM (Q4)
3.6GB
VRAM (FP16)
13.2GB
Image Generation

Stable Diffusion XL 1.0

Stability AI

Parameters
6.6B
Context
4K
VRAM (Q4)
3.6GB
VRAM (FP16)
13.2GB
Video Models

Sora

OpenAI

Parameters
0B
Context
4K
VRAM (Q4)
—
VRAM (FP16)
—
Large Language Models

Llama 4 Scout

Meta

Parameters
109B
Context
10000K
VRAM (Q4)
60GB
VRAM (FP16)
218GB
Large Language Models

Llama 3.3 70B

Meta

Parameters
70B
Context
128K
VRAM (Q4)
38.5GB
VRAM (FP16)
140GB
Large Language Models

GPT-4.1

OpenAI

Parameters
0B
Context
1048K
VRAM (Q4)
—
VRAM (FP16)
—
Large Language Models

Llama 3.1 405B

Meta

Parameters
405B
Context
128K
VRAM (Q4)
222.8GB
VRAM (FP16)
810GB
Large Language Models

Mistral 7B

Mistral AI

Parameters
7B
Context
33K
VRAM (Q4)
3.9GB
VRAM (FP16)
14GB
Large Language Models

Gemini 1.5 Pro

Google

Parameters
175B
Context
2000K
VRAM (Q4)
96.3GB
VRAM (FP16)
350GB
Large Language Models

GPT-4o Mini

OpenAI

Parameters
0B
Context
128K
VRAM (Q4)
—
VRAM (FP16)
—
Large Language Models

DeepSeek R1 Distill Llama 70B

DeepSeek

Parameters
70B
Context
128K
VRAM (Q4)
38.5GB
VRAM (FP16)
140GB
Large Language Models

Claude Sonnet 4.5

Anthropic

Parameters
120B
Context
200K
VRAM (Q4)
66GB
VRAM (FP16)
240GB
Large Language Models

Qwen2.5 Coder 32B

Alibaba

Parameters
32B
Context
131K
VRAM (Q4)
17.6GB
VRAM (FP16)
64GB
Image Generation

Stable Diffusion 1.5

Stability AI

Parameters
0.86B
Context
4K
VRAM (Q4)
0.47GB
VRAM (FP16)
1.72GB
Image Generation

FLUX.1 [dev]

Black Forest Labs

Parameters
12B
Context
4K
VRAM (Q4)
6.6GB
VRAM (FP16)
24GB
Image Generation

DALL·E 3

OpenAI

Parameters
12B
Context
4K
VRAM (Q4)
6.6GB
VRAM (FP16)
24GB
Video Models

Runway Gen-3 Alpha

Runway

Parameters
0B
Context
4K
VRAM (Q4)
—
VRAM (FP16)
—
Embedding Models

BGE Large EN v1.5

BAAI

Parameters
0.335B
Context
1K
VRAM (Q4)
0.18GB
VRAM (FP16)
0.67GB
Audio Models

Whisper Large v3 Turbo

OpenAI

Parameters
0.8B
Context
4K
VRAM (Q4)
0.44GB
VRAM (FP16)
1.6GB
Audio Models

ElevenLabs Multilingual v2

ElevenLabs

Parameters
1B
Context
4K
VRAM (Q4)
0.6GB
VRAM (FP16)
2GB
Large Language Models

Gemma 3 27B

Google

Parameters
27B
Context
128K
VRAM (Q4)
14.9GB
VRAM (FP16)
54GB
Large Language Models

DeepSeek R1 Distill Qwen 7B

DeepSeek

Parameters
7B
Context
128K
VRAM (Q4)
3.9GB
VRAM (FP16)
14GB
Large Language Models

GPT-4o

OpenAI

Parameters
0B
Context
128K
VRAM (Q4)
—
VRAM (FP16)
—
Large Language Models

Qwen3 235B-A22B

Alibaba

Parameters
235B
Context
131K
VRAM (Q4)
129.3GB
VRAM (FP16)
470GB
Large Language Models

Qwen3 8B

Alibaba

Parameters
8B
Context
131K
VRAM (Q4)
4.4GB
VRAM (FP16)
16GB
Large Language Models

GPT-4.1 mini

OpenAI

Parameters
0B
Context
1048K
VRAM (Q4)
—
VRAM (FP16)
—
Large Language Models

Mixtral 8x7B

Mistral AI

Parameters
46.7B
Context
33K
VRAM (Q4)
25.7GB
VRAM (FP16)
93.4GB
Large Language Models

DeepSeek V3

DeepSeek

Parameters
671B
Context
128K
VRAM (Q4)
369.1GB
VRAM (FP16)
1342GB
Multimodal Models

Gemini 2.0 Flash

Google

Parameters
30B
Context
1000K
VRAM (Q4)
16.5GB
VRAM (FP16)
60GB
Large Language Models

DeepSeek R1 Distill Qwen 32B

DeepSeek

Parameters
32B
Context
128K
VRAM (Q4)
17.6GB
VRAM (FP16)
64GB
Large Language Models

Claude Opus 4.1

Anthropic

Parameters
200B
Context
200K
VRAM (Q4)
110GB
VRAM (FP16)
400GB
Large Language Models

GPT-4o mini

OpenAI

Parameters
0B
Context
128K
VRAM (Q4)
—
VRAM (FP16)
—
Large Language Models

Llama 3.3 70B Instruct

Meta

Parameters
70B
Context
128K
VRAM (Q4)
42GB
VRAM (FP16)
140GB
Large Language Models

Qwen2.5 Coder 7B

Alibaba

Parameters
7B
Context
131K
VRAM (Q4)
3.9GB
VRAM (FP16)
14GB
Image Generation

FLUX.1 [schnell]

Black Forest Labs

Parameters
12B
Context
4K
VRAM (Q4)
6.6GB
VRAM (FP16)
24GB
Video Models

Veo 2

Google

Parameters
0B
Context
4K
VRAM (Q4)
—
VRAM (FP16)
—
Embedding Models

BGE-M3

BAAI

Parameters
0.568B
Context
8K
VRAM (Q4)
0.31GB
VRAM (FP16)
1.14GB
Embedding Models

All-MiniLM-L6-v2

Sentence Transformers

Parameters
0.022B
Context
0K
VRAM (Q4)
0.01GB
VRAM (FP16)
0.04GB
Large Language Models

Qwen3 32B

Alibaba

Parameters
32B
Context
131K
VRAM (Q4)
17.6GB
VRAM (FP16)
64GB
Large Language Models

Gemma 3 12B

Google

Parameters
12B
Context
128K
VRAM (Q4)
6.6GB
VRAM (FP16)
24GB

About the Model Database

HardwareHQ tracks 299 AI models from leading developers including Meta, Google, Mistral AI, Microsoft, Stability AI, and more. Each model profile includes parameter counts, VRAM requirements at every quantization level, context window sizes, and benchmarks.

Use the VRAM Calculator to check whether any model fits on your GPU, or browse the GPU Database to find the right hardware.

Explore more

VRAM Calculator

Check GPU compatibility for any AI model

Cloud GPU Pricing

Compare pricing across 24+ providers

GPU Comparison

Side-by-side GPU specs and benchmarks

Compatibility Lab

GPU × Model compatibility matrix

HQ
HardwareHQ

Free AI hardware database and decision tools — compare GPUs, check model fit, and track live cloud pricing.

Database

  • GPU Database
  • AI Model Database
  • GPU Comparison
  • Compatibility Matrix
  • AI Benchmarks
  • Model Finder

Market & Pricing

  • Cloud GPU Pricing
  • Buy vs Rent
  • Inference Calculator
  • Training Calculator
  • VRAM Calculator

Planning Studios

  • Research Studio
  • RAG Studio
  • Creative Studio
  • Coding Studio
  • Edge AI Studio
  • Hardware Architect
  • Topology Lab

Reference & Guides

  • LLM Requirements
  • Quantization Guide
  • Best GPU for LLaMA
  • Best GPU for DeepSeek
  • AI Homelab Guide

Company

  • About
  • Contact
  • Advertise
  • Privacy Policy
  • Terms of Service

© 2026 HardwareHQ. All rights reserved.

@HardwareHQio