Compatibility checker

Can I run this AI model on my GPU?

Pick a model and a GPU to get an instant, architecture-aware answer: whether it fits in full FP16, needs 8-bit or 4-bit quantization, or requires more than one card. Every estimate accounts for model weights plus the KV cache — the memory term most calculators ignore.

Popular models at a glance

Best precision each model fits at on common GPUs. Tap any cell to jump to that model's full per-precision breakdown on the GPU's page.

ModelRTX 409024 GBRTX 306012 GBRTX A600048 GBA100 80GB80 GB
Llama 3.2 3B InstructFP16FP16FP16FP16
Llama 3.1 8B InstructFP164/8-bitFP16FP16
Llama 3.1 70B InstructNoNo4/8-bit4/8-bit
Mistral 7B Instruct v0.3FP164/8-bitFP16FP16
Qwen2.5 7B InstructFP164/8-bitFP16FP16
Qwen2.5 32B Instruct4/8-bitNo4/8-bit4/8-bit
Gemma 2 9B Instruct4/8-bit4/8-bitFP16FP16
Gemma 2 27B Instruct4/8-bitNo4/8-bitFP16
Qwen2.5 3B InstructFP16FP16FP16FP16
Qwen2.5 14B Instruct4/8-bit4/8-bitFP16FP16
Qwen2.5 72B InstructNoNo4/8-bit4/8-bit
Qwen2.5 Coder 7B InstructFP164/8-bitFP16FP16
Qwen2.5 Coder 32B Instruct4/8-bitNo4/8-bit4/8-bit
Qwen3 8BFP164/8-bitFP16FP16
Qwen3 14B4/8-bit4/8-bitFP16FP16
Qwen3 32B4/8-bitNo4/8-bit4/8-bit
DeepSeek R1 Distill Qwen 7BFP164/8-bitFP16FP16
DeepSeek R1 Distill Qwen 14B4/8-bit4/8-bitFP16FP16
DeepSeek R1 Distill Qwen 32B4/8-bitNo4/8-bit4/8-bit
DeepSeek R1 Distill Llama 8BFP164/8-bitFP16FP16
Phi-3.5 Mini InstructFP16FP16FP16FP16
Phi-44/8-bit4/8-bitFP16FP16
Mistral Nemo Instruct4/8-bit4/8-bitFP16FP16
SmolLM2 1.7B InstructFP16FP16FP16FP16
Qwen2.5 0.5B InstructFP16FP16FP16FP16
Qwen2.5 1.5B InstructFP16FP16FP16FP16
Qwen2.5 Coder 1.5B InstructFP16FP16FP16FP16
Qwen2.5 Coder 14B Instruct4/8-bit4/8-bitFP16FP16
Qwen3 0.6BFP16FP16FP16FP16
Qwen3 1.7BFP16FP16FP16FP16
Qwen3 4BFP16FP16FP16FP16
QwQ 32B4/8-bitNo4/8-bit4/8-bit
DeepSeek R1 Distill Qwen 1.5BFP16FP16FP16FP16
DeepSeek R1 Distill Llama 70BNoNo4/8-bit4/8-bit
Mistral Small 24B Instruct4/8-bitNo4/8-bitFP16
Granite 3.1 8B InstructFP164/8-bitFP16FP16
OLMo 2 7B InstructFP164/8-bitFP16FP16
SmolLM2 360M InstructFP16FP16FP16FP16

FP16 = runs at full precision · 4/8-bit = fits with quantization · No = needs a bigger or additional GPU.

Browse by GPU

Pick your card to see every model it runs, and the precision each one needs.

How we decide if a model fits

Whether a model runs on a GPU comes down to three memory costs measured against the card's VRAM. First, the model weights: parameter count times bytes per parameter — 2 bytes in FP16, 1 in INT8, and about 0.5 in 4-bit. Second, the KV cache, which stores attention keys and values for every token in the context window and grows linearly with prompt length; it stays in FP16 even when the weights are quantized. Third, a runtime allowance for activations, CUDA context, and memory fragmentation. We add these up at a realistic context length and compare against the GPU, leaving roughly 10% headroom before calling a fit comfortable.

The practical upshot for buyers and builders: quantization is the lever that turns a "no" into a "yes" on consumer cards, but it has limits — a 70B model still needs an 80 GB card even at 4-bit, while an 8B model runs comfortably on a 12 GB card once quantized. For exact numbers at your own context length and batch size, use the VRAM Calculator, and to find the cheapest card that fits a given model, use the GPU Picker.