readygpu

NVIDIA GeForce RTX 5090 vs NVIDIA RTX 6000 Ada Generation

For running models locally, priced in the US. At 128k context the first runs 50 models fully in memory, the second 60.

In short

The NVIDIA RTX 6000 Ada Generation has more memory for models: 48 GB against 32 GB. At 128k context the NVIDIA RTX 6000 Ada Generation runs 60 of the models we track fully in memory and the NVIDIA GeForce RTX 5090 50; only the NVIDIA RTX 6000 Ada Generation holds Qwen 3.5 122B-A10B. On the models both run fully in memory, the NVIDIA GeForce RTX 5090 is about 1.9× as fast as the NVIDIA RTX 6000 Ada Generation (estimated, median across models).

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

NVIDIA GeForce RTX 5090

$4,921

eBay

Add to build
NVIDIA RTX 6000 Ada Generation

Not priced here

Add to build

Specifications

SpecNVIDIA GeForce RTX 5090NVIDIA RTX 6000 Ada Generation
GPUGeForce RTX 5090RTX 6000 Ada Generation
Memory32 GB GDDR748 GB GDDR6
Memory bus512-bit384-bit
Memory bandwidth1,792 GB/s960 GB/s
FP16 compute209 TFLOPS91.1 TFLOPS
SoftwareCUDACUDA
Board power575 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 5090NVIDIA RTX 6000 Ada Generation
Qwen 3.8 27B36tok/sUD-Q6_K16tok/sQ8_0
Qwen 3.5 122B-A10Boffload53tok/sUD-Q2_K_XL
Qwen 3.6 27B36tok/sQ6_K16tok/sQ8_0
Gemma 4 31B37tok/sQ4_K_M14tok/sQ8_0
Mistral Small 4 119Boffload66tok/sUD-Q2_K_XL
Qwen 3.6 35B-A3B128tok/sUD-Q6_K61tok/sQ8_0
Qwen 3.5 27B36tok/sQ6_K16tok/sQ8_0
Gemma 4 26B-A4B95tok/sQ8_051tok/sQ8_0
Qwen 3.5 35B-A3B129tok/sQ6_K61tok/sQ8_0
GLM 4.7 Flash60tok/sQ6_K29tok/sQ8_0
Devstral Small 2 24Boffload13tok/sQ8_0
Nemotron 3.5 Lightning 30B-A3B179tok/sUD-Q5_K_M86tok/sUD-Q6_K_XL
Kimi Linear 48B-A3B227tok/sQ4_K_M100tok/sQ6_K
gpt-oss 20B118tok/sMXFP463tok/sMXFP4
Qwen3 Coder 30B-A3B45tok/sQ4_K_M22tok/sQ8_0
Gemma 4 12B73tok/sQ8_039tok/sQ8_0
Qwen 3.5 9B80tok/sQ8_043tok/sQ8_0
Gemma 3 27B37tok/sQ5_K_M15tok/sQ8_0
Mistral Small 3.2 24Boffload13tok/sQ8_0
Ministral 3 14B36tok/sQ5_K_M17tok/sQ8_0
Qwen3 14B35tok/sQ5_K_M16tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B40tok/sQ8_021tok/sQ8_0
Qwen3 8B40tok/sQ8_021tok/sQ8_0
Phi-4 14Boffload14tok/sQ8_0
Qwen 3.5 4B126tok/sQ8_067tok/sQ8_0
Ministral 3 8B41tok/sQ8_022tok/sQ8_0
Granite 4.2 8B36tok/sQ8_019tok/sQ8_0
Gemma 4 E4B93tok/sQ8_050tok/sQ8_0
LFM2.5 8B-A1B89tok/sQ8_048tok/sQ8_0
Llama 3.1 8B47tok/sQ6_K25tok/sQ6_K
Qwen2.5 0.5B519tok/sQ8_0278tok/sQ8_0
Qwen3.5 0.8B455tok/sQ8_0244tok/sQ8_0
Qwen3.5 2B363tok/sQ5_K_M194tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B197tok/sQ8_0105tok/sQ8_0
Mellum2.1 12B A2.5B Thinking146tok/sQ8_078tok/sQ8_0
Spark X2.5 4B140tok/smlx-4bit75tok/smlx-4bit
MiniCPM5 2B134tok/sQ8_072tok/sQ8_0
FrogNano 4B 2609124tok/sQ8_066tok/sQ8_0
LFM2.5 2.6B102tok/sQ8_055tok/sQ8_0
LFM2.5 VL 3B102tok/sQ8_055tok/sQ8_0
Kimi VL A3B Thinking 250693tok/sQ8_050tok/sQ8_0
Kimi VL A3B91tok/smlx-8bit49tok/smlx-8bit
GLM 4 9B 041482tok/smlx-5bit44tok/smlx-5bit
granite vision 4.1 4b77tok/sQ8_042tok/sQ8_0
granite 4.2 3b76tok/sQ8_041tok/sQ8_0
GLM 4.6V Flash72tok/sQ8_039tok/sQ8_0
DeepSeek R1 Distill Qwen 7B71tok/sQ8_038tok/sQ8_0
GLM 4.1V 9B Thinking65tok/smlx-8bit35tok/smlx-8bit
Ministral 3 3B Instruct 251263tok/sQ8_034tok/sQ8_0
LFM2.5 24B A2B53tok/sQ6_K28tok/sQ8_0
Muse Glimmer 30B44tok/sQ6_K17tok/sQ8_0
DeepSeek R1 Distill Llama 8B43tok/sQ8_023tok/sQ8_0
Ministral 3 8B Reasoning 251241tok/sQ8_022tok/sQ8_0
Qwen3.8 27B OBLITERATED38tok/smlx-4bit20tok/smlx-4bit
Ministral 3 14B Reasoning 251236tok/sQ5_K_M17tok/sQ8_0
DeepSeek R1 Distill Qwen 14Boffload14tok/sQ8_0
Devstral Small 2507offload13tok/sQ8_0
Magistral Small 2506offload13tok/sQ8_0
Magistral Small 2507offload13tok/sQ8_0
Magistral Small 2509offload13tok/sQ8_0
Qwen3 Coder Nextoffloadoffload
Nemotron 3 Super 120B-A12Boffloadoffload
gpt-oss 120Bwon't runoffload
GLM 4.5 Airwon't runoffload
Qwen3 Next 80B-A3Boffloadoffload
Qwen3 32Boffloadoffload
DeepSeek R1 Distill Qwen 32Boffloadoffload
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
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 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 4.5Vwon'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

Questions

Which is better for local AI, the NVIDIA GeForce RTX 5090 or the NVIDIA RTX 6000 Ada Generation?
Choose the NVIDIA RTX 6000 Ada Generation to run bigger models. Choose the NVIDIA GeForce RTX 5090 for speed.
Which can run bigger models, the NVIDIA GeForce RTX 5090 or the NVIDIA RTX 6000 Ada Generation?
At 128k context the NVIDIA RTX 6000 Ada Generation runs 60 of the models we track fully in memory and the NVIDIA GeForce RTX 5090 50; only the NVIDIA RTX 6000 Ada Generation holds Qwen 3.5 122B-A10B.
Which is faster for local AI, the NVIDIA GeForce RTX 5090 or the NVIDIA RTX 6000 Ada Generation?
On the models both run fully in memory, the NVIDIA GeForce RTX 5090 is about 1.9× as fast as the NVIDIA RTX 6000 Ada Generation (estimated, median across models).

More comparisons

More hardware for local AI