GPUs with 8 GB VRAM for Running LLMs
Browse 12 GPUs with 8 GB VRAM compatible with running LLM models locally. Compare VRAM, memory bandwidth, and AI performance. Top picks and budget guide
12 GPUsClear filters
| GPU | Price |
|---|---|
| RTX 40608 GBGDDR6 · 272 GB/s · 115 WNVIDIA · Ada Lovelace · 2023 | about $520 |
| 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 Ti 8GB8 GBGDDR7 · 448 GB/s · 180 WNVIDIA · Blackwell · 2025 | about $379 |
| 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 3060 8GB8 GBGDDR6 · 240 GB/s · 170 WNVIDIA · Ampere · 2022 | about $329 |
| RTX 3060 Ti8 GBGDDR6 · 448 GB/s · 200 WNVIDIA · Ampere · 2020 | about $399 |
| RX 90508 GBGDDR6 · 288 GB/s · 92 WAMD · RDNA 4 · 2026 | about $279 |
| RTX 3070 Ti8 GBGDDR6X · 608 GB/s · 290 WNVIDIA · Ampere · 2021 | about $599 |
| RX 76008 GBGDDR6 · 288 GB/s · 165 WAMD · RDNA 3 · 2023 | about $269 |
| Arc A7508 GBGDDR6 · 512 GB/s · 225 WIntel · Alchemist · 2022 | about $289 |
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.