Sitemap
Tools
- LLM VRAM Calculator
- Can I Run It?
- Fine-Tuning VRAM Calculator
- Image & Video Model VRAM
- KV Cache Calculator
- GGUF Size Calculator
- Tokens per Second Estimator
Language models
- Llama 3.2 1B
- Llama 3.2 3B
- Llama 3.1 8B
- Llama 3.3 70B
- Llama 3.1 405B
- Llama 4 Scout
- Qwen 2.5 7B
- Qwen 2.5 14B
- Qwen 2.5 32B
- Qwen 2.5 Coder 32B
- Qwen 2.5 72B
- Qwen 3 4B
- Qwen 3 8B
- Qwen 3 14B
- Qwen 3 32B
- Qwen 3 30B-A3B
- Qwen 3 235B-A22B
- Qwen 3.5 4B
- Qwen 3.5 9B
- Qwen 3.5 27B
- Qwen 3.5 35B-A3B
- Qwen 3.5 122B-A10B
- Qwen 3.5 397B-A17B
- Qwen 3.6 27B
- Qwen 3.6 35B-A3B
- Qwen 3.8 27B
- Qwen3-Next 80B-A3B
- Qwen3-Coder 30B-A3B
- Mistral 7B v0.3
- Mistral Nemo 12B
- Mistral Small 3.1 24B
- Mixtral 8x7B
- Mistral Small 4 119B
- Ministral 3 3B
- Ministral 3 8B
- Ministral 3 14B
- Gemma 3 1B
- Gemma 3 4B
- Gemma 3 12B
- Gemma 3 27B
- Gemma 4 E2B
- Gemma 4 E4B
- Gemma 4 26B-A4B
- Gemma 4 31B
- Phi-4 Mini
- Phi-4 14B
- DeepSeek R1 671B
- DeepSeek R1 Distill Qwen 7B
- DeepSeek R1 Distill Llama 8B
- DeepSeek R1 Distill Qwen 14B
- DeepSeek R1 Distill Qwen 32B
- DeepSeek R1 Distill Llama 70B
- DeepSeek V4 Flash
- gpt-oss-20b
- gpt-oss-120b
- GLM-4.5-Air
- MiniMax-M2
- Kimi K2.6
Image and video models
- Stable Diffusion 1.5
- SDXL 1.0
- Stable Diffusion 3.5 Medium
- Stable Diffusion 3.5 Large
- FLUX.1 [dev]
- FLUX.1 [schnell]
- Qwen-Image
- Wan 2.2 A14B (T2V / I2V)
- Wan 2.2 TI2V 5B
- HunyuanVideo
- FLUX.1 Kontext [dev]
- FLUX.2 [dev]
- Z-Image Turbo
- Qwen-Image-Edit 2509
- LTX-2
GPUs and Macs
- RTX 2060 12GB
- RTX 2080 Ti 11GB
- RTX 3050 8GB
- RTX 3060 12GB
- RTX 3060 Ti 8GB
- RTX 3070 8GB
- RTX 3070 Ti 8GB
- RTX 3080 10GB
- RTX 3080 12GB
- RTX 3090 24GB
- RTX 3090 Ti 24GB
- RTX 4060 8GB
- RTX 4060 Ti 8GB
- RTX 4060 Ti 16GB
- RTX 4070 12GB
- RTX 4070 Super 12GB
- RTX 4070 Ti 12GB
- RTX 4070 Ti Super 16GB
- RTX 4080 16GB
- RTX 4080 Super 16GB
- RTX 4090 24GB
- RTX 5060 8GB
- RTX 5060 Ti 8GB
- RTX 5060 Ti 16GB
- RTX 5070 12GB
- RTX 5070 Ti 16GB
- RTX 5080 16GB
- RTX 5090 32GB
- Radeon RX 6700 XT 12GB
- Radeon RX 6800 XT 16GB
- Radeon RX 7600 8GB
- Radeon RX 7700 XT 12GB
- Radeon RX 7800 XT 16GB
- Radeon RX 7900 XT 20GB
- Radeon RX 7900 XTX 24GB
- Radeon RX 9060 XT 16GB
- Radeon RX 9070 XT 16GB
- Intel Arc A770 16GB
- Intel Arc B570 10GB
- Intel Arc B580 12GB
- RTX 6000 Ada 48GB
- RTX A6000 48GB
- RTX PRO 6000 Blackwell 96GB
- Radeon AI PRO R9700 32GB
- Intel Arc Pro B60 24GB
- A100 40GB
- A100 80GB
- H100 80GB SXM
- NVIDIA H200 141GB
- NVIDIA L4 24GB
- L40S 48GB
- Tesla P40 24GB
- Tesla T4 16GB
- AMD Instinct MI300X 192GB
- Apple M1 Max 64GB
- Apple M2 Ultra 192GB
- Apple M3 Max 128GB
- Apple M3 Ultra 512GB
- Apple M4 16GB
- Apple M4 Max 36GB
- Apple M4 Max 64GB
- Apple M4 Max 128GB
- Apple M4 Pro 24GB
- Apple M4 Pro 48GB
- Apple M5 32GB
- Apple M5 Max 128GB
- Apple M5 Pro 64GB
- NVIDIA DGX Spark 128GB
- Ryzen AI Max+ 395 128GB
VRAM tiers
Comparisons
- RTX 3060 12GB vs RTX 4060 Ti 16GB
- RTX 3090 24GB vs RTX 4090 24GB
- RTX 4090 24GB vs RTX 5090 32GB
- RTX 4060 Ti 16GB vs RTX 5060 Ti 16GB
- RTX 3090 24GB vs RTX 5070 Ti 16GB
- RTX 4090 24GB vs Radeon RX 7900 XTX 24GB
- RTX 5070 Ti 16GB vs Radeon RX 9070 XT 16GB
- Apple M4 Max 128GB vs RTX 5090 32GB
- A100 80GB vs H100 80GB SXM
- NVIDIA DGX Spark 128GB vs Ryzen AI Max+ 395 128GB
- RTX 3060 12GB vs RTX 3070 8GB
- RTX 3090 24GB vs RTX 4070 Ti Super 16GB
- Apple M4 Max 128GB vs Apple M4 Pro 48GB
- RTX 5060 Ti 16GB vs Radeon RX 9060 XT 16GB
- RTX 3090 24GB vs Radeon RX 7900 XTX 24GB
- RTX 5080 16GB vs RTX 5090 32GB
- RTX 5090 32GB vs RTX PRO 6000 Blackwell 96GB
- Apple M3 Ultra 512GB vs Apple M4 Max 128GB
- Apple M4 Max 128GB vs Apple M5 Max 128GB
- Intel Arc B580 12GB vs RTX 3060 12GB
- Apple M4 Max 128GB vs NVIDIA DGX Spark 128GB
- RTX 3090 24GB vs Tesla P40 24GB
- H100 80GB SXM vs NVIDIA H200 141GB
- RTX 4060 Ti 16GB vs RTX 4070 12GB
- Q4_K_M vs Q5_K_M
- Q4_K_M vs Q8_0
- FP16 / BF16 vs Q8_0
- IQ4_XS vs Q4_K_M
- Q3_K_M vs Q4_K_M
- Q5_K_M vs Q6_K
- FP8 vs Q8_0
- AWQ vs GGUF (Q4_K_M)
Guides
- How Much VRAM Do You Need to Run an LLM?
- Q4 vs Q5 vs Q8: Quantization Explained
- Best GPU for Local LLMs
- How to Run a 70B Model on Consumer GPUs
- Why Does My Model Use More VRAM Than Expected?
- Best Local LLMs for Every VRAM Size
- Ollama VRAM Settings That Actually Matter
- LM Studio GPU Offload Explained
- Best Mac for Local LLMs
- Best Local Coding Models for a 24 GB GPU
- Running Flux and Other Image Models on Low VRAM
- How Much VRAM Do You Need for AI Video?
- Multi-GPU Setups for Local LLMs
- KV Cache Explained
- Mixture-of-Experts Models and VRAM
- CPU Offloading: Running Models Bigger Than Your VRAM
- How Much VRAM Do You Need to Fine-Tune an LLM?
- Running Local LLMs on AMD GPUs