Which AI can your machine run?
Find out which AI models your machine can actually run.
Based on detected hardware
— of 83 models run well
GPU | VRAM | BW | RAM | CORES
Estimated from browser APIs — real specs may differ
0 Runs great 0 Runs well 0 OK 0 Tight 0 Barely runs 0 Too heavy
/
Your machine
Each bar is the memory a model needs at Q4_K_M quantization, measured on the same ruler across the page. Bars stopping before the orange line run comfortably. Bars crossing it need to borrow system RAM, which is much slower.
Llama 3.1 8B
▶
Qwen 3.5 9B
▶
Ornith 1.0 9B
▶
Phi-4 14B
▶
GPT-OSS 20B
▶
Mistral Small 3.1 24B
▶
Gemma 3 27B
▶
Qwen 2.5 Coder 32B
▶
Qwen 3 32B
▶
DeepSeek R1 Distill 32B
▶
Ornith 1.0 35B-A3B
▶
Llama 3.3 70B
▶
Llama 4 Scout 17B
▶
GPT-OSS 120B
▶
Devstral 2 123B
▶
DeepSeek R1
▶
DeepSeek V3.2
▶
GLM-5.2
▶
Kimi K2
▶
All models
Qwen 3 0.6B
▶
Qwen 3.5 0.8B
▶
Llama 3.2 1B
▶
Gemma 3 1B
▶
TinyLlama 1.1B
▶
Qwen 2.5 Coder 1.5B
▶
DeepSeek R1 1.5B
▶
Qwen 3 1.7B
▶
Qwen 3.5 2B
▶
Gemma 2 2B
▶
Llama 3.2 3B
▶
SmolLM3 3B
▶
Phi-3.5 Mini
▶
Phi-4 Mini Reasoning
▶
Qwen 3 4B
▶
Gemma 3 4B
▶
Qwen 3.5 4B
▶
Gemma 4 E2B IT
▶
Gemma 4 E2B
▶
Mistral 7B v0.3
▶
Qwen 2.5 7B
▶
Qwen 2.5 Coder 7B
▶
DeepSeek R1 Distill 7B
▶
Gemma 4 E4B IT
▶
Gemma 4 E4B
▶
Qwen 3 8B
▶
Ministral 8B
▶
Gemma 2 9B
▶
GLM-4 9B
▶
Nemotron Nano 9B v2
▶
Llama 3.2 11B Vision
▶
Gemma 3 12B
▶
Mistral Nemo 12B
▶
Qwen 2.5 14B
▶
Qwen 3 14B
▶
DeepSeek R1 Distill 14B
▶
LFM2 24B
▶
Devstral Small 2 24B
▶
DiffusionGemma 26B-A4B IT
▶
Gemma 2 27B
▶
Gemma 4 26B-A4B IT
▶
Gemma 4 26B-A4B
▶
Qwen 3.5 27B
▶
Qwen 3 30B-A3B
▶
Nemotron 3 Nano 30B
▶
Qwen 2.5 32B
▶
EXAONE 4.0 32B
▶
OLMo 2 32B
▶
Gemma 4 31B IT
▶
Gemma 4 31B
▶
Command R 35B
▶
Qwen 3.5 35B-A3B
▶
Mixtral 8x7B
▶
Qwen 2.5 72B
▶
Qwen 3.5 122B-A10B
▶
Mixtral 8x22B
▶
Qwen 3 235B-A22B
▶
Qwen 3.5 397B-A17B
▶
Llama 4 Maverick 17B-128E
▶
Llama 3.1 405B
▶
Qwen 3 Coder 480B
▶
DeepSeek V3.1
▶
GLM-5
▶
GLM-5.1
▶
No models found
Try adjusting your search or filters.