What LLM fits my GPU? – VRAM measured on real hard
Pick your graphics card and see which of 117 quantized LLMs actually fit it — at which quant level, with how much VRAM spare, and the command to run each.
Pick your graphics card and see which of 117 quantized LLMs actually fit it — at which quant level, with how much VRAM spare, and the command to run each.
What LLM fits my GPU? — 117-model VRAM index | quantized.uk quantized .uk Home Quant Hub GPUs Benchmarks Cookbook Tools My GPU RTX 5090 ( 32 G) RTX 5080 ( 16 G) RTX 5070 Ti ( 16 G) RTX 5070 ( 12 G) RTX 5060 Ti 16G ( 16 G) RTX 5060 Ti 8G ( 8 G) RTX 5060 ( 8 G) RTX 5050 ( 8 G) RTX 4090 ( 24 G) RTX 4080 Super ( 16 G) RTX 4070 Ti Super ( 16 G) RTX 4070 Ti ( 12 G) RTX 4070 Super ( 12 G) RTX 4070 ( 12 G) RTX 4060 Ti 16G ( 16 G) RTX 4060 Ti 8G ( 8 G) RTX 4060 ( 8 G) RTX 3090 ( 24 G) RTX 3080 Ti ( 12 G) RTX 3080 12G ( 12 G) RTX 3080 10G ( 10 G) RTX 3070 Ti ( 8 G) RTX 3070 ( 8 G) RTX 3060 12G ( 12 G) A
Pick your graphics card and see which of 117 quantized LLMs actually fit it — at which quant level, with how much VRAM spare, and the command to run each.
What LLM fits my GPU? — 117-model VRAM index | quantized.uk quantized .uk Home Quant Hub GPUs Benchmarks Cookbook Tools My GPU RTX 5090 ( 32 G) RTX 5080 ( 16 G) RTX 5070 Ti ( 16 G) RTX 5070 ( 12 G) RTX 5060 Ti 16G ( 16 G) RTX 5060 Ti 8G ( 8 G) RTX 5060 ( 8 G) RTX 5050 ( 8 G) RTX 4090 ( 24 G) RTX 4080 Super ( 16 G) RTX 4070 Ti Super ( 16 G) RTX 4070 Ti ( 12 G) RTX 4070 Super ( 12 G) RTX 4070 ( 12 G) RTX 4060 Ti 16G ( 16 G) RTX 4060 Ti 8G ( 8 G) RTX 4060 ( 8 G) RTX 3090 ( 24 G) RTX 3080 Ti ( 12 G) RTX 3080 12G ( 12 G) RTX 3080 10G ( 10 G) RTX 3070 Ti ( 8 G) RTX 3070 ( 8 G) RTX 3060 12G ( 12 G) A
