Hardware
Everything to pick, install and run open models on your own computer.
Open modelsWill it run?Setup guidesLicensesHardwareCheat sheetsProjectsCompare modelsGlossaryRoadmapInterview Q&AFree resources
Hardware
What you can run depends mostly on memory: how much RAM you have, and whether your graphics card has enough video memory to hold the model. This page lists common RAM sizes with the kind of model each one suits, along with cloud GPU options, so you can decide whether to use the computer you have or rent a GPU by the hour.
| Computer | Largest 4-bit model (estimate) | Good for |
|---|---|---|
| 8 GB RAM | Mistral 7B Instruct v0.3 | Learning and small models (about 3B parameters or less) |
| 16 GB RAM | Gemma 2 9B | 7B to 8B models for chat and coding help, for example Llama 3.1 8B (about 4.9 GB) or Mistral 7B (about 4.4 GB) |
| 32 GB RAM | Gemma 2 9B | Mid-size models around 14B to 27B, for example Qwen2.5 14B (9 GB) or Gemma 2 27B (16 GB) |
| 64 GB RAM | Llama 3.1 70B | Large models such as Qwen2.5 32B (20 GB) or Llama 3.1 70B (43 GB), with enough free memory left over |

