readygpu

NVIDIA GeForce RTX 5090 vs AMD Radeon RX 9060 XT 16GB

For running models locally, priced in the US. At 32k context the first runs 52 models fully in memory, the second 29.

In short

The NVIDIA GeForce RTX 5090 has more memory for models: 32 GB against 16 GB. At 32k context the NVIDIA GeForce RTX 5090 runs 52 of the models we track fully in memory and the AMD Radeon RX 9060 XT 16GB 29; only the NVIDIA GeForce RTX 5090 holds Qwen 3.8 27B. On the models both run fully in memory, the NVIDIA GeForce RTX 5090 is about 6.3× as fast as the AMD Radeon RX 9060 XT 16GB (estimated, median across models). In the US the NVIDIA GeForce RTX 5090 costs $4,921 at eBay and the AMD Radeon RX 9060 XT 16GB $520 at Amazon: the AMD Radeon RX 9060 XT 16GB is $4,401 cheaper.

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

NVIDIA GeForce RTX 5090

$4,921

eBay

Add to build
AMD Radeon RX 9060 XT 16GB

$520

Amazon

Add to build

Specifications

SpecNVIDIA GeForce RTX 5090AMD Radeon RX 9060 XT 16GB
GPUGeForce RTX 5090Radeon RX 9060 XT 16GB
Memory32 GB GDDR716 GB GDDR6
Memory bus512-bit128-bit
Memory bandwidth1,792 GB/s320 GB/s
FP16 compute209 TFLOPS103 TFLOPS
SoftwareCUDAROCm
Board power575 W160 W
PCIe generationGen 5Gen 5
PCIe lanesx16x16

What each runs

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

ModelNVIDIA GeForce RTX 5090AMD Radeon RX 9060 XT 16GB
Qwen 3.8 27B35tok/sQ8_0offload
Qwen 3.6 27B36tok/sQ8_0offload
Gemma 4 31B39tok/sQ6_Koffload
Qwen 3.6 35B-A3B201tok/sQ6_Koffload
Qwen 3.5 27B36tok/sQ8_0offload
Gemma 4 26B-A4B132tok/sQ8_0offload
Qwen 3.5 35B-A3B212tok/sQ6_Koffload
GLM 4.7 Flash114tok/sQ6_Koffload
Devstral Small 2 24B37tok/sQ8_0offload
Kimi Linear 48B-A3B311tok/sQ4_K_Moffload
gpt-oss 20B206tok/sMXFP433tok/sMXFP4
Qwen3 Coder 30B-A3B117tok/sQ6_Koffload
Qwen3 32B35tok/sQ5_K_Moffload
Gemma 4 12B82tok/sQ8_013tok/sQ8_0
Qwen 3.5 9B104tok/sQ8_017tok/sQ8_0
Mistral Small 3.2 24B37tok/sQ8_0offload
DeepSeek R1 Distill Qwen 32B35tok/sQ5_K_Moffload
Gemma 3 27B35tok/sQ8_0offload
Ministral 3 14B56tok/sQ8_012tok/sQ5_K_M
Qwen3 14B53tok/sQ8_012tok/sQ4_K_M
DeepSeek R1 0528 Qwen3 8B82tok/sQ8_013tok/sQ8_0
Qwen3 8B82tok/sQ8_013tok/sQ8_0
Phi-4 14B50tok/sQ8_0offload
Qwen 3.5 4B198tok/sQ8_031tok/sQ8_0
Ministral 3 8B82tok/sQ8_013tok/sQ8_0
Granite 4.2 8B76tok/sQ8_012tok/sQ8_0
Gemma 4 E4B121tok/sQ8_019tok/sQ8_0
LFM2.5 8B-A1B249tok/sQ8_040tok/sQ8_0
Llama 3.1 8B102tok/sQ6_K16tok/sQ6_K
Qwen2.5 0.5B1190tok/sQ8_0189tok/sQ8_0
Qwen3.5 0.8B901tok/sQ8_0143tok/sQ8_0
Qwen3.5 2B598tok/sQ5_K_M95tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B392tok/sQ8_062tok/sQ8_0
MiniCPM5 2B272tok/sQ8_043tok/sQ8_0
LFM2.5 2.6B227tok/sQ8_036tok/sQ8_0
LFM2.5 VL 3B227tok/sQ8_036tok/sQ8_0
Mellum2.1 12B A2.5B Thinking210tok/sQ8_033tok/sQ8_0
granite vision 4.1 4b176tok/sQ8_028tok/sQ8_0
granite 4.2 3b169tok/sQ8_027tok/sQ8_0
Kimi VL A3B156tok/smlx-8bit30tok/smlx-6bit
LFM2.5 24B A2B139tok/sQ8_0offload
DeepSeek R1 Distill Qwen 7B111tok/sQ8_018tok/sQ8_0
GLM 4.6V Flash98tok/sQ8_016tok/sQ8_0
DeepSeek R1 Distill Llama 8B87tok/sQ8_014tok/sQ8_0
GLM 4.1V 9B Thinking85tok/smlx-8bit13tok/smlx-8bit
Ministral 3 8B Reasoning 251282tok/sQ8_013tok/sQ8_0
DeepSeek R1 Distill Qwen 14B50tok/sQ8_0offload
granite 4.2 30b38tok/sQ5_K_Moffload
Devstral Small 250737tok/sQ8_0offload
Magistral Small 250637tok/sQ8_0offload
Magistral Small 250737tok/sQ8_0offload
Magistral Small 250937tok/sQ8_0offload
Qwen 3.5 122B-A10Boffloadoffload
Qwen3 Coder Nextoffloadwon't run
Nemotron 3 Super 120B-A12Boffloadwon't run
Mistral Small 4 119Boffloadoffload
GLM 4.5 Airoffloadwon't run
Qwen3 Next 80B-A3Boffloadwon't run
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
Llama 3.3 70Boffloadwon't run
DeepSeek R1 Distill Llama 70Boffloadwon't run
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
gpt-oss 120Bwon't runwon't run
DeepSeek R1won't runwon't run
DeepSeek R1 0528won'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 5090 or the AMD Radeon RX 9060 XT 16GB?
Choose the NVIDIA GeForce RTX 5090 to run bigger models. Choose the NVIDIA GeForce RTX 5090 for speed. Choose the AMD Radeon RX 9060 XT 16GB to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 5090 or the AMD Radeon RX 9060 XT 16GB?
At 32k context the NVIDIA GeForce RTX 5090 runs 52 of the models we track fully in memory and the AMD Radeon RX 9060 XT 16GB 29; only the NVIDIA GeForce RTX 5090 holds Qwen 3.8 27B.
Which is faster for local AI, the NVIDIA GeForce RTX 5090 or the AMD Radeon RX 9060 XT 16GB?
On the models both run fully in memory, the NVIDIA GeForce RTX 5090 is about 6.3× as fast as the AMD Radeon RX 9060 XT 16GB (estimated, median across models).
What is the price difference between the NVIDIA GeForce RTX 5090 and the AMD Radeon RX 9060 XT 16GB?
In the US the NVIDIA GeForce RTX 5090 costs $4,921 at eBay and the AMD Radeon RX 9060 XT 16GB $520 at Amazon: the AMD Radeon RX 9060 XT 16GB is $4,401 cheaper.

More comparisons