readygpu

NVIDIA GeForce RTX 4090 vs NVIDIA GeForce RTX 5060 Ti 16GB

For running models locally, priced in the US. At 32k context the first runs 48 models fully in memory, the second 30.

In short

The NVIDIA GeForce RTX 4090 has more memory for models: 24 GB against 16 GB. At 32k context the NVIDIA GeForce RTX 4090 runs 48 of the models we track fully in memory and the NVIDIA GeForce RTX 5060 Ti 16GB 30; only the NVIDIA GeForce RTX 4090 holds Qwen 3.8 27B. On the models both run fully in memory, the NVIDIA GeForce RTX 4090 is about 2.3× as fast as the NVIDIA GeForce RTX 5060 Ti 16GB (estimated, median across models). In the US the NVIDIA GeForce RTX 4090 costs $2,073 at eBay and the NVIDIA GeForce RTX 5060 Ti 16GB $618 at eBay: the NVIDIA GeForce RTX 5060 Ti 16GB is $1,456 cheaper.

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

NVIDIA GeForce RTX 4090

$2,073

eBay

Add to build
NVIDIA GeForce RTX 5060 Ti 16GB

$618

eBay

Add to build

Specifications

SpecNVIDIA GeForce RTX 4090NVIDIA GeForce RTX 5060 Ti 16GB
GPUGeForce RTX 4090GeForce RTX 5060 Ti 16GB
Memory24 GB GDDR6X16 GB GDDR7
Memory bus384-bit128-bit
Memory bandwidth1,008 GB/s448 GB/s
FP16 compute165 TFLOPS47 TFLOPS
SoftwareCUDACUDA
Board power450 W180 W
PCIe generationGen 4Gen 5
PCIe lanesx16x8

What each runs

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

ModelNVIDIA GeForce RTX 4090NVIDIA GeForce RTX 5060 Ti 16GB
Qwen 3.8 27B27tok/sQ5_K_Moffload
Qwen 3.6 27B29tok/sQ5_K_Moffload
Gemma 4 31B29tok/sQ4_K_Moffload
Qwen 3.6 35B-A3B145tok/sQ4_K_Moffload
Qwen 3.5 27B29tok/sQ5_K_Moffload
Gemma 4 26B-A4B84tok/sUD-Q6_Koffload
Qwen 3.5 35B-A3B146tok/sQ4_K_Moffload
GLM 4.7 Flash70tok/sQ5_K_Moffload
Devstral Small 2 24B28tok/sQ5_K_Moffload
gpt-oss 20B116tok/sMXFP452tok/sMXFP4
Qwen3 Coder 30B-A3B74tok/sQ4_K_Moffload
Gemma 4 12B46tok/sQ8_021tok/sQ8_0
Qwen 3.5 9B59tok/sQ8_026tok/sQ8_0
Mistral Small 3.2 24B28tok/sQ5_K_Moffload
Gemma 3 27B28tok/sQ5_K_Moffload
Ministral 3 14B32tok/sQ8_019tok/sQ5_K_M
Qwen3 14B30tok/sQ8_019tok/sQ4_K_M
DeepSeek R1 0528 Qwen3 8B46tok/sQ8_021tok/sQ8_0
Qwen3 8B46tok/sQ8_021tok/sQ8_0
Phi-4 14B28tok/sQ8_0offload
Qwen 3.5 4B112tok/sQ8_050tok/sQ8_0
Ministral 3 8B46tok/sQ8_020tok/sQ8_0
Granite 4.2 8B43tok/sQ8_019tok/sQ8_0
Gemma 4 E4B68tok/sQ8_030tok/sQ8_0
LFM2.5 8B-A1B140tok/sQ8_062tok/sQ8_0
Llama 3.1 8B57tok/sQ6_K26tok/sQ6_K
Qwen2.5 0.5B669tok/sQ8_0298tok/sQ8_0
Qwen3.5 0.8B507tok/sQ8_0225tok/sQ8_0
Qwen3.5 2B337tok/sQ5_K_M150tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B221tok/sQ8_098tok/sQ8_0
MiniCPM5 2B153tok/sQ8_068tok/sQ8_0
LFM2.5 2.6B128tok/sQ8_057tok/sQ8_0
LFM2.5 VL 3B128tok/sQ8_057tok/sQ8_0
Mellum2.1 12B A2.5B Thinking118tok/sQ8_053tok/sQ8_0
granite vision 4.1 4b99tok/sQ8_044tok/sQ8_0
granite 4.2 3b95tok/sQ8_042tok/sQ8_0
Kimi VL A3B88tok/smlx-8bit47tok/smlx-6bit
LFM2.5 24B A2B84tok/sQ6_Koffload
DeepSeek R1 Distill Qwen 7B63tok/sQ8_028tok/sQ8_0
GLM 4.6V Flash55tok/sQ8_025tok/sQ8_0
DeepSeek R1 Distill Llama 8B49tok/sQ8_022tok/sQ8_0
GLM 4.1V 9B Thinking48tok/smlx-8bit21tok/smlx-8bit
Ministral 3 8B Reasoning 251246tok/sQ8_020tok/sQ8_0
DeepSeek R1 Distill Qwen 14B28tok/sQ8_018tok/sQ4_K_M
Devstral Small 250728tok/sQ5_K_Moffload
Magistral Small 250628tok/sQ5_K_Moffload
Magistral Small 250728tok/sQ5_K_Moffload
Magistral Small 250928tok/sQ5_K_Moffload
Qwen 3.5 122B-A10Boffloadoffload
Qwen3 Coder Nextoffloadwon't run
Mistral Small 4 119Boffloadoffload
GLM 4.5 Airoffloadwon't run
Qwen3 Next 80B-A3Boffloadwon't run
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
Kimi Linear 48B-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
Nemotron 3 Super 120B-A12Bwon't runwon't run
gpt-oss 120Bwon'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 4090 or the NVIDIA GeForce RTX 5060 Ti 16GB?
Choose the NVIDIA GeForce RTX 4090 to run bigger models. Choose the NVIDIA GeForce RTX 4090 for speed. Choose the NVIDIA GeForce RTX 5060 Ti 16GB to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 4090 or the NVIDIA GeForce RTX 5060 Ti 16GB?
At 32k context the NVIDIA GeForce RTX 4090 runs 48 of the models we track fully in memory and the NVIDIA GeForce RTX 5060 Ti 16GB 30; only the NVIDIA GeForce RTX 4090 holds Qwen 3.8 27B.
Which is faster for local AI, the NVIDIA GeForce RTX 4090 or the NVIDIA GeForce RTX 5060 Ti 16GB?
On the models both run fully in memory, the NVIDIA GeForce RTX 4090 is about 2.3× as fast as the NVIDIA GeForce RTX 5060 Ti 16GB (estimated, median across models).
What is the price difference between the NVIDIA GeForce RTX 4090 and the NVIDIA GeForce RTX 5060 Ti 16GB?
In the US the NVIDIA GeForce RTX 4090 costs $2,073 at eBay and the NVIDIA GeForce RTX 5060 Ti 16GB $618 at eBay: the NVIDIA GeForce RTX 5060 Ti 16GB is $1,456 cheaper.

More comparisons