readygpu

NVIDIA GeForce RTX 5080 vs NVIDIA RTX A6000

For running models locally, priced in the US. At 64k context the first runs 32 models fully in memory, the second 64.

In short

The NVIDIA RTX A6000 has more memory for models: 48 GB against 16 GB. At 64k context the NVIDIA RTX A6000 runs 64 of the models we track fully in memory and the NVIDIA GeForce RTX 5080 32; only the NVIDIA RTX A6000 holds Qwen 3.8 27B. On the models both run fully in memory, the NVIDIA GeForce RTX 5080 is about 1.3× as fast as the NVIDIA RTX A6000 (estimated, median across models). In the US the NVIDIA GeForce RTX 5080 costs $2,100 at eBay and the NVIDIA RTX A6000 $4,899 at eBay (used): the NVIDIA GeForce RTX 5080 is $2,799 cheaper.

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

NVIDIA GeForce RTX 5080

$2,100

eBay

Add to build
NVIDIA RTX A6000

$4,470

eBay

Add to build

Specifications

SpecNVIDIA GeForce RTX 5080NVIDIA RTX A6000
GPUGeForce RTX 5080RTX A6000
Memory16 GB GDDR748 GB GDDR6
Memory bus256-bit384-bit
Memory bandwidth960 GB/s768 GB/s
FP16 compute113 TFLOPS38.71 TFLOPS
SoftwareCUDACUDA
Board power360 W300 W
PCIe generationGen 5Gen 4
PCIe lanesx16x16

What each runs

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

ModelNVIDIA GeForce RTX 5080NVIDIA RTX A6000
Qwen 3.8 27Boffload14tok/sQ8_0
Qwen 3.5 122B-A10Bwon't run56tok/sUD-Q2_K_XL
Qwen 3.6 27Boffload14tok/sQ8_0
Gemma 4 31Boffload12tok/sQ8_0
Mistral Small 4 119Boffload74tok/sUD-Q2_K_XL
Qwen 3.6 35B-A3Boffload64tok/sQ8_0
Qwen 3.5 27Boffload14tok/sQ8_0
Gemma 4 26B-A4Boffload50tok/sQ8_0
Qwen 3.5 35B-A3Boffload64tok/sQ8_0
GLM 4.7 Flashoffload32tok/sQ8_0
Devstral Small 2 24Boffload13tok/sQ8_0
Nemotron 3.5 Lightning 30B-A3Boffload76tok/sUD-Q6_K_XL
gpt-oss 20B88tok/sMXFP471tok/sMXFP4
Kimi Linear 48B-A3Boffload94tok/sQ6_K
Qwen3 Coder 30B-A3Boffload30tok/sQ8_0
Qwen3 32Boffload11tok/sQ6_K
Gemma 4 12B42tok/sQ8_034tok/sQ8_0
Qwen 3.5 9B51tok/sQ8_041tok/sQ8_0
Gemma 3 27Boffload14tok/sQ8_0
Mistral Small 3.2 24Boffload13tok/sQ8_0
DeepSeek R1 Distill Qwen 32Boffload11tok/sQ6_K
Ministral 3 14Boffload19tok/sQ8_0
Qwen3 14Boffload18tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B41tok/sQ4_K_M26tok/sQ8_0
Qwen3 8B41tok/sQ4_K_M26tok/sQ8_0
Phi-4 14Boffload16tok/sQ8_0
Qwen 3.5 4B89tok/sQ8_071tok/sQ8_0
Ministral 3 8B39tok/sQ5_K_M26tok/sQ8_0
Granite 4.2 8Boffload24tok/sQ8_0
Gemma 4 E4B59tok/sQ8_047tok/sQ8_0
LFM2.5 8B-A1B83tok/sQ8_067tok/sQ8_0
Llama 3.1 8B39tok/sQ6_K31tok/sQ6_K
Qwen2.5 0.5B445tok/sQ8_0356tok/sQ8_0
Qwen3.5 0.8B364tok/sQ8_0291tok/sQ8_0
Qwen3.5 2B263tok/sQ5_K_M211tok/sQ5_K_M
LFM3 1.7B224tok/sQ8_0179tok/sQ8_0
DeepSeek R1 Distill Qwen 1.5B158tok/sQ8_0126tok/sQ8_0
MiniCPM5 2B108tok/sQ8_087tok/sQ8_0
Spark X2.5 4B108tok/smlx-4bit86tok/smlx-4bit
Mellum2.1 12B A2.5B Thinking98tok/sQ8_078tok/sQ8_0
Kimi VL A3B Thinking 250690tok/sQ4_K_M56tok/sQ8_0
FrogNano 4B 260987tok/sQ8_070tok/sQ8_0
LFM2.5 2.6B86tok/sQ8_069tok/sQ8_0
LFM2.5 VL 3B86tok/sQ8_069tok/sQ8_0
Kimi VL A3B85tok/smlx-5bit54tok/smlx-8bit
granite vision 4.1 4b66tok/sQ8_053tok/sQ8_0
granite 4.2 3b64tok/sQ8_051tok/sQ8_0
Ministral 3 3B Instruct 251256tok/sQ8_045tok/sQ8_0
GLM 4 9B 041454tok/smlx-5bit44tok/smlx-5bit
DeepSeek R1 Distill Qwen 7B50tok/sQ8_040tok/sQ8_0
GLM 4.6V Flash47tok/sQ8_038tok/sQ8_0
GLM 4.1V 9B Thinking41tok/smlx-8bit33tok/smlx-8bit
DeepSeek R1 Distill Llama 8B39tok/sQ6_K28tok/sQ8_0
Ministral 3 8B Reasoning 251239tok/sQ5_K_M26tok/sQ8_0
LFM2.5 24B A2Boffload38tok/sQ8_0
Muse Glimmer 30Boffload14tok/sQ8_0
Ministral 3 14B Reasoning 2512offload19tok/sQ8_0
DeepSeek R1 Distill Qwen 14Boffload17tok/sQ8_0
Devstral Small 2507offload13tok/sQ8_0
Magistral Small 2506offload13tok/sQ8_0
Magistral Small 2507offload13tok/sQ8_0
Magistral Small 2509offload13tok/sQ8_0
Qwen3.8 27B OBLITERATEDoffload19tok/smlx-4bit
granite 4.2 30boffload10tok/sQ8_0
Nemotron 3 Super 120B-A12Bwon't runoffload
Qwen3 Coder Nextwon't runoffload
gpt-oss 120Bwon't runoffload
GLM 4.5 Airwon't runoffload
Qwen3 Next 80B-A3Bwon't runoffload
Llama 3.3 70Bwon't runoffload
DeepSeek R1 Distill Llama 70Bwon't runoffload
GLM 4.5Vwon't runoffload
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
DeepSeek R1won't runwon't run
DeepSeek R1 0528won't runwon't run
DeepSeek R1 Zerowon't runwon't run
DeepSeek V3won'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 4.5won'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

Questions

Which is better for local AI, the NVIDIA GeForce RTX 5080 or the NVIDIA RTX A6000?
Choose the NVIDIA RTX A6000 to run bigger models. Choose the NVIDIA GeForce RTX 5080 for speed. Choose the NVIDIA GeForce RTX 5080 to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 5080 or the NVIDIA RTX A6000?
At 64k context the NVIDIA RTX A6000 runs 64 of the models we track fully in memory and the NVIDIA GeForce RTX 5080 32; only the NVIDIA RTX A6000 holds Qwen 3.8 27B.
Which is faster for local AI, the NVIDIA GeForce RTX 5080 or the NVIDIA RTX A6000?
On the models both run fully in memory, the NVIDIA GeForce RTX 5080 is about 1.3× as fast as the NVIDIA RTX A6000 (estimated, median across models).
What is the price difference between the NVIDIA GeForce RTX 5080 and the NVIDIA RTX A6000?
In the US the NVIDIA GeForce RTX 5080 costs $2,100 at eBay and the NVIDIA RTX A6000 $4,899 at eBay (used): the NVIDIA GeForce RTX 5080 is $2,799 cheaper.

More comparisons

More hardware for local AI