readygpu

NVIDIA GeForce RTX 3090 vs AMD Radeon RX 9060 XT 16GB

For running models locally, priced in the US. At 64k context the first runs 40 models fully in memory, the second 26.

In short

The NVIDIA GeForce RTX 3090 has more memory for models: 24 GB against 16 GB. At 64k context the NVIDIA GeForce RTX 3090 runs 40 of the models we track fully in memory and the AMD Radeon RX 9060 XT 16GB 26; only the NVIDIA GeForce RTX 3090 holds Qwen 3.8 27B. On the models both run fully in memory, the NVIDIA GeForce RTX 3090 is about 3.3× as fast as the AMD Radeon RX 9060 XT 16GB (estimated, median across models). In the US the NVIDIA GeForce RTX 3090 costs $1,600 at eBay and the AMD Radeon RX 9060 XT 16GB $520 at Amazon: the AMD Radeon RX 9060 XT 16GB is $1,080 cheaper.

Updated . Speeds are estimates; how they are worked out.

NVIDIA GeForce RTX 3090

$1,600

eBay

Add to build
AMD Radeon RX 9060 XT 16GB

$520

Amazon

Add to build

Specifications

SpecNVIDIA GeForce RTX 3090AMD Radeon RX 9060 XT 16GB
GPUGeForce RTX 3090Radeon RX 9060 XT 16GB
Memory24 GB GDDR6X16 GB GDDR6
Memory bus384-bit128-bit
Memory bandwidth936 GB/s320 GB/s
FP16 compute71 TFLOPS103 TFLOPS
SoftwareCUDAROCm
Board power350 W160 W
PCIe generationGen 4Gen 5
PCIe lanesx16x16

What each runs

Estimated decode speed with the most precise quant that fits each one est.

ModelNVIDIA GeForce RTX 3090AMD Radeon RX 9060 XT 16GB
Qwen 3.8 27B27tok/sQ4_K_Moffload
Qwen 3.6 27B24tok/sQ5_K_Moffload
Qwen 3.6 35B-A3B107tok/sQ4_K_Moffload
Qwen 3.5 27B27tok/sQ4_K_Moffload
Gemma 4 26B-A4B72tok/sUD-Q5_K_Moffload
Qwen 3.5 35B-A3B107tok/sQ4_K_Moffload
GLM 4.7 Flash53tok/sQ4_K_Moffload
gpt-oss 20B86tok/sMXFP426tok/sMXFP4
Gemma 4 12B41tok/sQ8_013tok/sQ8_0
Qwen 3.5 9B50tok/sQ8_015tok/sQ8_0
Gemma 3 27B26tok/sQ4_K_Moffload
Ministral 3 14B27tok/sQ6_Koffload
Qwen3 14B25tok/sQ6_Koffload
DeepSeek R1 0528 Qwen3 8B32tok/sQ8_012tok/sQ4_K_M
Qwen3 8B32tok/sQ8_012tok/sQ4_K_M
Phi-4 14B24tok/sQ5_K_Moffload
Qwen 3.5 4B87tok/sQ8_026tok/sQ8_0
Ministral 3 8B32tok/sQ8_012tok/sQ4_K_M
Granite 4.2 8B29tok/sQ8_0offload
Gemma 4 E4B57tok/sQ8_017tok/sQ8_0
LFM2.5 8B-A1B81tok/sQ8_025tok/sQ8_0
Llama 3.1 8B38tok/sQ6_K12tok/sQ5_K_M
Qwen2.5 0.5B434tok/sQ8_0132tok/sQ8_0
Qwen3.5 0.8B355tok/sQ8_0108tok/sQ8_0
Qwen3.5 2B257tok/sQ5_K_M78tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B154tok/sQ8_047tok/sQ8_0
MiniCPM5 2B106tok/sQ8_032tok/sQ8_0
Mellum2.1 12B A2.5B Thinking96tok/sQ8_029tok/sQ8_0
LFM2.5 2.6B84tok/sQ8_026tok/sQ8_0
LFM2.5 VL 3B84tok/sQ8_026tok/sQ8_0
Kimi VL A3B66tok/smlx-8bit25tok/smlx-5bit
granite vision 4.1 4b65tok/sQ8_020tok/sQ8_0
granite 4.2 3b63tok/sQ8_019tok/sQ8_0
LFM2.5 24B A2B50tok/sQ5_K_Moffload
DeepSeek R1 Distill Qwen 7B49tok/sQ8_015tok/sQ8_0
GLM 4.6V Flash46tok/sQ8_014tok/sQ8_0
GLM 4.1V 9B Thinking40tok/smlx-8bit12tok/smlx-8bit
DeepSeek R1 Distill Llama 8B34tok/sQ8_012tok/sQ5_K_M
Ministral 3 8B Reasoning 251232tok/sQ8_012tok/sQ4_K_M
DeepSeek R1 Distill Qwen 14B25tok/sQ5_K_Moffload
Qwen 3.5 122B-A10Boffloadwon't run
Gemma 4 31Boffloadoffload
Qwen3 Coder Nextoffloadwon't run
Mistral Small 4 119Boffloadoffload
Qwen3 Next 80B-A3Boffloadwon't run
Devstral Small 2 24Boffloadoffload
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
Kimi Linear 48B-A3Boffloadoffload
Qwen3 Coder 30B-A3Boffloadoffload
Qwen3 32Boffloadoffload
Mistral Small 3.2 24Boffloadoffload
DeepSeek R1 Distill Qwen 32Boffloadoffload
Devstral Small 2507offloadoffload
Magistral Small 2506offloadoffload
Magistral Small 2507offloadoffload
Magistral Small 2509offloadoffload
granite 4.2 30boffloadoffload
DeepSeek V4 Flashwon't runwon't run
GLM 5.3 Flashwon't runwon't run
Qwen 3.8 Flash Nextwon't runwon't run
MiniMax M2.7won't runwon't run
Nemotron 3 Super 120B-A12Bwon't runwon't run
gpt-oss 120Bwon't runwon't run
GLM 4.5 Airwon't runwon't run
Llama 3.3 70Bwon't runwon't run
DeepSeek R1won't runwon't run
DeepSeek R1 0528won't runwon't run
DeepSeek R1 Distill Llama 70Bwon't runwon't run
DeepSeek V3 0324won't runwon't run
DeepSeek V3.1won't runwon't run
DeepSeek V3.2won't runwon't run
DeepSeek V4 Flash 0731won't runwon't run
DeepSeek V4 Flash Vision Expwon't runwon't run
Devstral 2 123B Instruct 2512won't runwon't run
GLM 4.5Vwon't runwon't run
GLM 4.6Vwon't runwon't run
GLM 4.7won't runwon't run
GLM 5.1won't runwon't run
GLM 5.2won't runwon't run
GLM 5.3won't runwon't run
Kimi K2won't runwon't run
Kimi K2 Instruct 0905won't runwon't run
Kimi K2 Thinkingwon't runwon't run
Kimi K2.5won't runwon't run
MiniMax M2won't runwon't run
MiniMax M2.1won't runwon't run
MiniMax M2.5won't runwon't run
MiniMax M3won't runwon't run
Mistral Medium 3.5 128Bwon't runwon't run

Questions

Which is better for local AI, the NVIDIA GeForce RTX 3090 or the AMD Radeon RX 9060 XT 16GB?
Choose the NVIDIA GeForce RTX 3090 to run bigger models. Choose the NVIDIA GeForce RTX 3090 for speed. Choose the AMD Radeon RX 9060 XT 16GB to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 3090 or the AMD Radeon RX 9060 XT 16GB?
At 64k context the NVIDIA GeForce RTX 3090 runs 40 of the models we track fully in memory and the AMD Radeon RX 9060 XT 16GB 26; only the NVIDIA GeForce RTX 3090 holds Qwen 3.8 27B.
Which is faster for local AI, the NVIDIA GeForce RTX 3090 or the AMD Radeon RX 9060 XT 16GB?
On the models both run fully in memory, the NVIDIA GeForce RTX 3090 is about 3.3× as fast as the AMD Radeon RX 9060 XT 16GB (estimated, median across models).
What is the price difference between the NVIDIA GeForce RTX 3090 and the AMD Radeon RX 9060 XT 16GB?
In the US the NVIDIA GeForce RTX 3090 costs $1,600 at eBay and the AMD Radeon RX 9060 XT 16GB $520 at Amazon: the AMD Radeon RX 9060 XT 16GB is $1,080 cheaper.

More comparisons