GPUs with 4–11 GB VRAM for Running LLMs
Browse 74 GPUs with 4–11 GB VRAM compatible with running LLM models locally. Compare VRAM, memory bandwidth, and AI performance. Top picks and budget guide
74 GPUs
| GPU | Price |
|---|---|
| RTX 40608 GBGDDR6 · 272 GB/s · 115 WNVIDIA · Ada Lovelace · 2023 | about $520 |
| RTX 4060 Laptop GPULaptop8 GBGDDR6 · 256 GB/s · 115 WNVIDIA · Ada Lovelace · 2023 | – |
| RTX 4060 Ti 8GB8 GBGDDR6 · 288 GB/s · 160 WNVIDIA · Ada Lovelace · 2023 | about $399 |
| RTX 50608 GBGDDR7 · 448 GB/s · 145 WNVIDIA · Blackwell · 2025 | about $460 |
| RTX 5060 Laptop GPULaptop8 GBGDDR7 · 384 GB/s · 100 WNVIDIA · Blackwell · 2025 | – |
| RTX 2080 Ti11 GBGDDR6 · 616 GB/s · 250 WNVIDIA · Turing · 2018 | about $999 |
| RTX 308010 GBGDDR6X · 760 GB/s · 320 WNVIDIA · Ampere · 2020 | about $699 |
| RTX 4070 Laptop GPULaptop8 GBGDDR6 · 256 GB/s · 115 WNVIDIA · Ada Lovelace · 2023 | – |
| RTX 5060 Ti 8GB8 GBGDDR7 · 448 GB/s · 180 WNVIDIA · Blackwell · 2025 | about $379 |
| RTX 5070 Laptop GPULaptop8 GBGDDR7 · 384 GB/s · 100 WNVIDIA · Blackwell · 2025 | – |
| GTX 1660 SUPER6 GBGDDR6 · 336 GB/s · 125 WNVIDIA · Turing · 2019 | about $229 |
| GTX 1660 Ti6 GBGDDR6 · 288 GB/s · 120 WNVIDIA · Turing · 2019 | about $279 |
| RTX 2070 SUPER8 GBGDDR6 · 448 GB/s · 215 WNVIDIA · Turing · 2019 | about $499 |
| RTX 3050 8GB8 GBGDDR6 · 224 GB/s · 130 WNVIDIA · Ampere · 2022 | about $249 |
| RTX 30708 GBGDDR6 · 448 GB/s · 220 WNVIDIA · Ampere · 2020 | about $499 |
| RTX 3070 Laptop GPULaptop8 GBGDDR6 · 448 GB/s · 125 WNVIDIA · Ampere · 2021 | – |
| RTX 2060 Laptop GPULaptop6 GBGDDR6 · 336 GB/s · 90 WNVIDIA · Turing · 2019 | – |
| RTX 20808 GBGDDR6 · 448 GB/s · 215 WNVIDIA · Turing · 2018 | about $699 |
| RTX 2080 SUPER8 GBGDDR6 · 496 GB/s · 250 WNVIDIA · Turing · 2019 | about $699 |
| RTX 2060 SUPER8 GBGDDR6 · 448 GB/s · 175 WNVIDIA · Turing · 2019 | about $399 |
| RTX 20708 GBGDDR6 · 448 GB/s · 175 WNVIDIA · Turing · 2018 | about $499 |
| RTX 3060 8GB8 GBGDDR6 · 240 GB/s · 170 WNVIDIA · Ampere · 2022 | about $329 |
| RTX 3060 Laptop GPULaptop6 GBGDDR6 · 336 GB/s · 115 WNVIDIA · Ampere · 2021 | – |
| RTX 3080 Laptop GPULaptop8 GBGDDR6 · 448 GB/s · 150 WNVIDIA · Ampere · 2021 | – |
| RTX 3060 Ti8 GBGDDR6 · 448 GB/s · 200 WNVIDIA · Ampere · 2020 | about $399 |
Which GPU Do You Need for AI?
The amount of VRAM is the most important specification for running LLMs locally. Most 7B parameter models require 4–8 GB of VRAM at common quantization levels, while 70B models need 24–48 GB. Memory bandwidth determines how fast the model generates tokens — faster bandwidth means faster responses.