Open-weight LLMs you can run yourself › Mistral 7B Instruct v0.2
Updated · public data
Mistral AI · Open weights
Mistral 7B Instruct v0.2 is an open-weight LLM from Mistral AI with 7.2B parameters. It needs about 4 GB of memory at 4-bit — smallest setups that run it: PC with a GPU 8 GB, PC or laptop, no GPU 16 GB, Mac 16 GB.
| Parameters | 7.2B |
| Memory to run | ~4 GB (at 4-bit, rough estimate) |
| Downloads | 1.6M (last 30 days on Hugging Face) |
| Likes | 3.3K |
| License | Apache 2.0 |
| First uploaded | Dec 11, 2023 |
| Hosted from | not hosted |
| Phone | iPhone · Android: too big |
| PC with a GPU | 8 GB: fits · 12 GB: fits · 16 GB: fits · 24 GB: fits · 32 GB: fits |
| PC or laptop, no GPU | 16 GB: fits · 32 GB: fits · 64 GB: fits |
| Mac | 16 GB: fits · 32 GB: fits · 64 GB: fits · 128 GB: fits |
huggingface.co/mistralai/Mistral-7B-Instruct-v0.2
Data: Hugging Face (official accounts), Oct 16, 2026 · memory is a rough estimate (4-bit for LLMs, 8-bit for image and video, plus 10%) · hosted price: OpenRouter