readygpu

NVIDIA GeForce RTX 3060 12GB vs AMD Radeon RX 7800 XT

For running models locally, priced in the US. At 128k context the first runs 13 models fully in memory, the second 21.

In short

The AMD Radeon RX 7800 XT has more memory for models: 16 GB against 12 GB. At 128k context the AMD Radeon RX 7800 XT runs 21 of the models we track fully in memory and the NVIDIA GeForce RTX 3060 12GB 13; only the AMD Radeon RX 7800 XT holds LFM2.5 8B-A1B. On the models both run fully in memory, the AMD Radeon RX 7800 XT is about 1.5× as fast as the NVIDIA GeForce RTX 3060 12GB (estimated, median across models). In the US the NVIDIA GeForce RTX 3060 12GB costs $370 at Amazon and the AMD Radeon RX 7800 XT $691 at eBay: the NVIDIA GeForce RTX 3060 12GB is $321 cheaper.

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

NVIDIA GeForce RTX 3060 12GB

$370

Amazon

Add to build
AMD Radeon RX 7800 XT

$691

eBay

Add to build

Specifications

SpecNVIDIA GeForce RTX 3060 12GBAMD Radeon RX 7800 XT
GPUGeForce RTX 3060 12GBRadeon RX 7800 XT
Memory12 GB GDDR616 GB GDDR6
Memory bus192-bit256-bit
Memory bandwidth360 GB/s624 GB/s
FP16 compute25.6 TFLOPS74 TFLOPS
SoftwareCUDAROCm
Board power170 W263 W
PCIe generationGen 4Gen 4
PCIe lanesx16x16

What each runs

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

ModelNVIDIA GeForce RTX 3060 12GBAMD Radeon RX 7800 XT
Gemma 4 12B23tok/sQ4_K_M28tok/sQ6_K
Qwen 3.5 9B22tok/sQ4_K_M25tok/sQ8_0
Qwen 3.5 4B25tok/sQ8_039tok/sQ8_0
Gemma 4 E4B24tok/sQ5_K_M29tok/sQ8_0
LFM2.5 8B-A1Boffload28tok/sUD-Q6_K
Qwen2.5 0.5B104tok/sQ8_0160tok/sQ8_0
Qwen3.5 0.8B91tok/sQ8_0141tok/sQ8_0
Qwen3.5 2B73tok/sQ5_K_M112tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B40tok/sQ8_061tok/sQ8_0
Spark X2.5 4B28tok/smlx-4bit43tok/smlx-4bit
MiniCPM5 2B27tok/sQ8_041tok/sQ8_0
FrogNano 4B 260925tok/sQ8_038tok/sQ8_0
LFM2.5 2.6B22tok/sQ6_K31tok/sQ8_0
LFM2.5 VL 3B22tok/sQ6_K31tok/sQ8_0
Mellum2.1 12B A2.5B Thinkingoffload48tok/sQ6_K
GLM 4.6V Flashoffload30tok/sQ4_K_M
DeepSeek R1 Distill Qwen 7Boffload25tok/sQ6_K
GLM 4 9B 0414offload25tok/smlx-5bit
Kimi VL A3B Thinking 2506offload34tok/sQ4_K_M
granite vision 4.1 4boffload24tok/sQ8_0
granite 4.2 3boffload24tok/sQ8_0
Qwen 3.8 27Boffloadoffload
Qwen 3.6 27Boffloadoffload
Gemma 4 31Boffloadoffload
Qwen 3.6 35B-A3Boffloadoffload
Qwen 3.5 27Boffloadoffload
Gemma 4 26B-A4Boffloadoffload
Qwen 3.5 35B-A3Boffloadoffload
GLM 4.7 Flashoffloadoffload
Devstral Small 2 24Boffloadoffload
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
Kimi Linear 48B-A3Boffloadoffload
gpt-oss 20Boffloadoffload
Qwen3 Coder 30B-A3Boffloadoffload
Gemma 3 27Boffloadoffload
Mistral Small 3.2 24Boffloadoffload
Ministral 3 14Boffloadoffload
Qwen3 14Boffloadoffload
DeepSeek R1 0528 Qwen3 8Boffloadoffload
Qwen3 8Boffloadoffload
Phi-4 14Boffloadoffload
Ministral 3 8Boffloadoffload
Granite 4.2 8Boffloadoffload
Llama 3.1 8Boffloadoffload
Kimi VL A3Boffloadoffload
GLM 4.1V 9B Thinkingoffloadoffload
LFM2.5 24B A2Boffloadoffload
DeepSeek R1 Distill Llama 8Boffloadoffload
Ministral 3 8B Reasoning 2512offloadoffload
Qwen3.8 27B OBLITERATEDoffloadoffload
DeepSeek R1 Distill Qwen 14Boffloadoffload
Devstral Small 2507offloadoffload
Magistral Small 2506offloadoffload
Magistral Small 2507offloadoffload
Magistral Small 2509offloadoffload
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
Qwen 3.5 122B-A10Bwon't runwon't run
Nemotron 3 Super 120B-A12Bwon't runwon't run
Qwen3 Coder Nextwon't runwon't run
gpt-oss 120Bwon't runwon't run
Mistral Small 4 119Bwon't runwon't run
GLM 4.5 Airwon't runwon't run
Qwen3 Next 80B-A3Bwon't runwon't run
Qwen3 32Bwon't runwon't run
DeepSeek R1 Distill Qwen 32Bwon'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 R1 Zerowon't runwon't run
DeepSeek V3 0324won't runwon't run
DeepSeek V3.1won't runwon't run
DeepSeek V3.1 Terminuswon'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 4.6won't runwon't run
GLM 4.6Vwon't runwon't run
GLM 4.7won't runwon't run
GLM 5won'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 Dev 72Bwon'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
granite 4.2 30bwon't runwon't run

Questions

Which is better for local AI, the NVIDIA GeForce RTX 3060 12GB or the AMD Radeon RX 7800 XT?
Choose the AMD Radeon RX 7800 XT to run bigger models. Choose the AMD Radeon RX 7800 XT for speed. Choose the NVIDIA GeForce RTX 3060 12GB to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 3060 12GB or the AMD Radeon RX 7800 XT?
At 128k context the AMD Radeon RX 7800 XT runs 21 of the models we track fully in memory and the NVIDIA GeForce RTX 3060 12GB 13; only the AMD Radeon RX 7800 XT holds LFM2.5 8B-A1B.
Which is faster for local AI, the NVIDIA GeForce RTX 3060 12GB or the AMD Radeon RX 7800 XT?
On the models both run fully in memory, the AMD Radeon RX 7800 XT is about 1.5× as fast as the NVIDIA GeForce RTX 3060 12GB (estimated, median across models).
What is the price difference between the NVIDIA GeForce RTX 3060 12GB and the AMD Radeon RX 7800 XT?
In the US the NVIDIA GeForce RTX 3060 12GB costs $370 at Amazon and the AMD Radeon RX 7800 XT $691 at eBay: the NVIDIA GeForce RTX 3060 12GB is $321 cheaper.

More comparisons