GPUs with 10–12 GB VRAM for Running LLMs
Browse 14 GPUs with 10–12 GB VRAM compatible with running LLM models locally. Compare VRAM, memory bandwidth, and AI performance. Top picks and budget guide
14 GPUsClear filters
| GPU | Price |
|---|---|
| RTX 507012 GBGDDR7 · 672 GB/s · 250 WNVIDIA · Blackwell · 2025 | about $840 |
| RTX 4070 SUPER12 GBGDDR6X · 504 GB/s · 220 WNVIDIA · Ada Lovelace · 2024 | about $599 |
| RTX 4070 Ti12 GBGDDR6X · 504 GB/s · 285 WNVIDIA · Ada Lovelace · 2023 | about $799 |
| RX 9070 GRE12 GBGDDR6 · 432 GB/s · 220 WAMD · RDNA 4 · 2026 | about $549 |
| RTX 407012 GBGDDR6X · 504 GB/s · 200 WNVIDIA · Ada Lovelace · 2023 | about $599 |
| RTX 3060 12GB12 GBGDDR6 · 360 GB/s · 170 WNVIDIA · Ampere · 2021 | about $329 |
| 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 3080 Ti12 GBGDDR6X · 912 GB/s · 350 WNVIDIA · Ampere · 2021 | about $1,199 |
| RX 7700 XT12 GBGDDR6 · 432 GB/s · 245 WAMD · RDNA 3 · 2023 | about $449 |
| Arc B57010 GBGDDR6 · 380 GB/s · 150 WIntel · Xe2 · 2025 | about $219 |
| Arc B58012 GBGDDR6 · 456 GB/s · 190 WIntel · Battlemage · 2024 | about $249 |
| GTX 1080 Ti11 GBGDDR5X · 484 GB/s · 250 WNVIDIA · Pascal · 2017 | about $699 |
| RX 6700 XT12 GBGDDR6 · 384 GB/s · 230 WAMD · RDNA 2 · 2021 | about $479 |
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.