Every model and GPU guide in one place. Pick a model to see its VRAM across quantizations, or a GPU to see which LLMs it can run.

VRAM by AI model (107)

VRAM for bge-large-en-v1.5 (335M) VRAM for bge-m3 (567M) VRAM for bge-reranker-large (335M) VRAM for ChatTTS (132M) VRAM for Codestral 25.01 (24B) VRAM for CogVideoX (2B) VRAM for CogVideoX (5B) VRAM for DeepSeek-Coder-V2 (236B) VRAM for DeepSeek-Coder-V2 Lite (16B) VRAM for DeepSeek-R1 (671B Full) VRAM for DeepSeek-R1 (70B Distill) VRAM for DeepSeek-R1 Distill (1.5B) VRAM for DeepSeek-R1 Distill (14B) VRAM for DeepSeek-R1 Distill (32B) VRAM for DeepSeek-R1 Distill (7B) VRAM for DeepSeek-R1 Distill (8B) VRAM for DeepSeek-V3.1 (671B) VRAM for DeepSeek-V4-Flash (284B-A13B) VRAM for DeepSeek-V4-Pro (1.6T MoE) VRAM for Devstral Small (24B) VRAM for EmbeddingGemma (308M) VRAM for F5-TTS (38M) VRAM for Fish Speech (300M) VRAM for FLUX.1 Dev (12B) VRAM for FLUX.1 Schnell (12B) VRAM for FLUX.2 Dev (32B) VRAM for Gemma 2 (9B) VRAM for Gemma 3 (12B) VRAM for Gemma 3 (1B) VRAM for Gemma 3 (27B) VRAM for Gemma 3 (4B) VRAM for Gemma 3n (E2B) VRAM for Gemma 4 (26B MoE) VRAM for GLM-4.5 Air (106B-A12B) VRAM for GLM-4.6 (355B-A32B) VRAM for GLM-5.2 (744B-A40B MoE) VRAM for gpt-oss (120B MoE) VRAM for gpt-oss (20B MoE) VRAM for HunyuanVideo (13B) VRAM for InternVL3 (78B) VRAM for InternVL3 (8B) VRAM for jina-embeddings-v3 (570M) VRAM for jina-reranker-v2 (300M) VRAM for Kimi K2 (1T MoE) VRAM for Kokoro (82M) VRAM for Llama 3.1 (405B) VRAM for Llama 3.1 (8B) VRAM for Llama 3.2 (3B) VRAM for Llama 3.2 Vision (11B) VRAM for Llama 3.2 Vision (90B) VRAM for Llama 3.3 (70B) VRAM for Llama 4 Maverick (400B MoE) VRAM for Llama 4 Scout (109B MoE) VRAM for LLaVA 1.6 (8B) VRAM for LTX-Video (13B) VRAM for LTX-Video (2B) VRAM for MiniMax M3 (428B-A23B MoE) VRAM for Mistral Large 2 (123B) VRAM for Mochi 1 (10B) VRAM for nomic-embed-text v1.5 (137M) VRAM for nomic-embed-text v2 MoE (475M) VRAM for Parakeet TDT (0.6B) VRAM for Phi-4 (14B) VRAM for Phi-4 Mini (3.8B) VRAM for Phi-4 Multimodal (5.6B) VRAM for PixArt-Sigma (0.6B) VRAM for Pixtral (12B) VRAM for Qwen 2.5 (32B) VRAM for Qwen 2.5 Coder (0.5B) VRAM for Qwen 2.5 Coder (1.5B) VRAM for Qwen 2.5 Coder (14B) VRAM for Qwen 2.5 Coder (32B) VRAM for Qwen 2.5 Coder (3B) VRAM for Qwen 2.5 Coder (7B) VRAM for Qwen 2.5 VL (3B) VRAM for Qwen 2.5 VL (72B) VRAM for Qwen 2.5 VL (7B) VRAM for Qwen 3 (0.6B) VRAM for Qwen 3 (1.7B) VRAM for Qwen 3 (14B) VRAM for Qwen 3 (30B-A3B MoE) VRAM for Qwen 3 (32B) VRAM for Qwen 3 (4B) VRAM for Qwen 3 (8B) VRAM for Qwen 3 Coder (30B-A3B MoE) VRAM for Qwen 3 Coder (480B-A35B) VRAM for Qwen 3 Embedding (0.6B) VRAM for Qwen 3 Reranker (0.6B) VRAM for Qwen 3 VL (32B) VRAM for Qwen 3 VL (4B) VRAM for Qwen 3 VL (8B) VRAM for Qwen 3.6 (27B) VRAM for Qwen 3.6 (35B-A3B MoE) VRAM for Qwen-Image (20B) VRAM for SmolLM3 (3B) VRAM for Stable Diffusion 1.5 VRAM for Stable Diffusion 3.5 Large (8B) VRAM for Stable Diffusion 3.5 Med (2.5B) VRAM for Stable Diffusion XL (SDXL) VRAM for StarCoder 2 (15B) VRAM for StarCoder 2 (3B) VRAM for StarCoder 2 (7B) VRAM for stella-en-400M (435M) VRAM for Wan 2.2 (14B MoE) VRAM for Whisper Large V3 (1.55B) VRAM for XTTS v2 (2.4B) VRAM for Z-Image Turbo (6B)

AI models by GPU (109)

Models for AMD Instinct MI300X (CDNA 3) Models for AMD Instinct MI325X (CDNA 3) Models for AMD Radeon 890M / Intel Xe Integrated Models for AMD Radeon RX 5500 XT Models for AMD Radeon RX 5600 XT Models for AMD Radeon RX 5700 Models for AMD Radeon RX 5700 XT Models for AMD Radeon RX 6600 Models for AMD Radeon RX 6600 XT Models for AMD Radeon RX 6700 XT Models for AMD Radeon RX 6750 XT Models for AMD Radeon RX 6800 Models for AMD Radeon RX 6800 XT Models for AMD Radeon RX 6900 XT Models for AMD Radeon RX 6950 XT Models for AMD Radeon RX 7600 Models for AMD Radeon RX 7600 XT Models for AMD Radeon RX 7600M XT Mobile Models for AMD Radeon RX 7700 XT Models for AMD Radeon RX 7800 XT Models for AMD Radeon RX 7900 GRE Models for AMD Radeon RX 7900 XT Models for AMD Radeon RX 7900 XTX Models for AMD Radeon RX 7900M Laptop GPU Models for AMD Radeon RX 9060 XT (16GB) Models for AMD Radeon RX 9070 (RDNA 4) Models for AMD Radeon RX 9070 XT (RDNA 4) Models for Apple M1 Max Models for Apple M1 Ultra Models for Apple M2 Max Models for Apple M2 Ultra (Dual Max) Models for Apple M3 Base Models for Apple M3 Max Models for Apple M3 Pro Models for Apple M3 Ultra (Mac Studio) Models for Apple M4 Base (Entry SoC) Models for Apple M4 Max (14-Core CPU, 32-Core GPU) Models for Apple M4 Max (16-Core CPU, 40-Core GPU) Models for Apple M4 Pro Models for Apple M5 Base (Entry SoC) Models for Apple M5 Max (16-Core CPU, 40-Core GPU) Models for Apple M5 Pro Models for Intel Arc / AMD Radeon Graphics (Lunar/Panther Lake) Models for Intel Arc A380 Models for Intel Arc A580 Models for Intel Arc A750 Models for Intel Arc A770 (16GB) Models for Intel Arc B570 Models for Intel Arc B580 Models for Multi-RTX 4090 / 3090 Node Models for Nvidia A100 Tensor Core 80GB Models for Nvidia Blackwell B100 Tensor Core Models for Nvidia Blackwell B200 Tensor Core Models for Nvidia GH200 Grace Hopper Superchip Models for Nvidia GTX 1650 Models for Nvidia GTX 1650 Super Models for Nvidia GTX 1660 Super Models for Nvidia GTX 1660 Ti Models for Nvidia H100 SXM5 / PCIe Models for Nvidia Hopper H200 (HBM3e) Models for Nvidia L4 Tensor Core Models for Nvidia L40S Models for Nvidia RTX 2060 Models for Nvidia RTX 2060 Super Models for Nvidia RTX 2070 Models for Nvidia RTX 2070 Super Models for Nvidia RTX 2080 Models for Nvidia RTX 2080 Super Models for Nvidia RTX 2080 Ti Models for Nvidia RTX 3050 Models for Nvidia RTX 3060 (12GB) Models for Nvidia RTX 3060 (8GB) Models for Nvidia RTX 3060 Ti Models for Nvidia RTX 3070 Models for Nvidia RTX 3070 Ti Models for Nvidia RTX 3080 (10GB) Models for Nvidia RTX 3080 (12GB) Models for Nvidia RTX 3080 Ti Models for Nvidia RTX 3090 Models for Nvidia RTX 3090 Ti Models for Nvidia RTX 4050 Laptop GPU Models for Nvidia RTX 4060 Models for Nvidia RTX 4060 Laptop GPU Models for Nvidia RTX 4060 Ti (16GB) Models for Nvidia RTX 4060 Ti (8GB) Models for Nvidia RTX 4070 Models for Nvidia RTX 4070 Laptop GPU Models for Nvidia RTX 4070 Super Models for Nvidia RTX 4070 Ti Models for Nvidia RTX 4070 Ti Super Models for Nvidia RTX 4080 Models for Nvidia RTX 4080 Laptop GPU Models for Nvidia RTX 4080 Super Models for Nvidia RTX 4090 Models for Nvidia RTX 4090 Laptop GPU Models for Nvidia RTX 5050 Models for Nvidia RTX 5060 Models for Nvidia RTX 5060 Laptop GPU Models for Nvidia RTX 5060 Ti (16GB) Models for Nvidia RTX 5070 Models for Nvidia RTX 5070 Laptop GPU (12GB) Models for Nvidia RTX 5070 Laptop GPU (8GB) Models for Nvidia RTX 5070 Ti Models for Nvidia RTX 5080 Models for Nvidia RTX 5080 Laptop GPU Models for Nvidia RTX 5090 Models for Nvidia RTX 5090 Laptop GPU Models for Nvidia RTX 6000 Ada Gen Models for Nvidia RTX A6000
Get the exact number for your setup
Pick your model, quantization, and context length — the calculator shows the full VRAM math and tells you precisely which hardware fits.
Open the Local AI Calculator