readygpu

NVIDIA GeForce RTX 4060 vs NVIDIA GeForce RTX 4090

For running models locally, priced in the US. At 64k context the first runs 11 models fully in memory, the second 49.

In short

The NVIDIA GeForce RTX 4090 has more memory for models: 24 GB against 8 GB. At 64k context the NVIDIA GeForce RTX 4090 runs 49 of the models we track fully in memory and the NVIDIA GeForce RTX 4060 11; 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 3.7× as fast as the NVIDIA GeForce RTX 4060 (estimated, median across models). In the US the NVIDIA GeForce RTX 4060 costs $530 at eBay and the NVIDIA GeForce RTX 4090 $2,073 at eBay: the NVIDIA GeForce RTX 4060 is $1,543 cheaper.

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

NVIDIA GeForce RTX 4060

$530

eBay

Add to build
NVIDIA GeForce RTX 4090

$2,073

eBay

Add to build

Specifications

SpecNVIDIA GeForce RTX 4060NVIDIA GeForce RTX 4090
GPUGeForce RTX 4060GeForce RTX 4090
Memory8 GB GDDR624 GB GDDR6X
Memory bus128-bit384-bit
Memory bandwidth272 GB/s1,008 GB/s
FP16 compute15.114 TFLOPS165 TFLOPS
SoftwareCUDACUDA
Board power115 W450 W
PCIe generationGen 4Gen 4
PCIe lanesx8x16

What each runs

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

ModelNVIDIA GeForce RTX 4060NVIDIA GeForce RTX 4090
Qwen 3.8 27Boffload29tok/sQ4_K_M
Qwen 3.6 27Boffload26tok/sQ5_K_M
Qwen 3.6 35B-A3Boffload115tok/sQ4_K_M
Qwen 3.5 27Boffload30tok/sQ4_K_M
Gemma 4 26B-A4Boffload78tok/sUD-Q5_K_M
Qwen 3.5 35B-A3Boffload116tok/sQ4_K_M
GLM 4.7 Flashoffload57tok/sQ4_K_M
Nemotron 3.5 Lightning 30B-A3Boffload141tok/sMXFP4
gpt-oss 20Boffload93tok/sMXFP4
Gemma 4 12Boffload44tok/sQ8_0
Qwen 3.5 9Boffload53tok/sQ8_0
Gemma 3 27Boffload28tok/sQ4_K_M
Ministral 3 14Boffload29tok/sQ6_K
Qwen3 14Boffload27tok/sQ6_K
DeepSeek R1 0528 Qwen3 8Boffload34tok/sQ8_0
Qwen3 8Boffload34tok/sQ8_0
Phi-4 14Boffload26tok/sQ5_K_M
Qwen 3.5 4B25tok/sQ8_094tok/sQ8_0
Ministral 3 8Boffload34tok/sQ8_0
Granite 4.2 8Boffload31tok/sQ8_0
Gemma 4 E4Boffload62tok/sQ8_0
LFM2.5 8B-A1Boffload88tok/sQ8_0
Llama 3.1 8Boffload41tok/sQ6_K
Qwen2.5 0.5B126tok/sQ8_0468tok/sQ8_0
Qwen3.5 0.8B103tok/sQ8_0382tok/sQ8_0
Qwen3.5 2B75tok/sQ5_K_M277tok/sQ5_K_M
LFM3 1.7B63tok/sQ8_0235tok/sQ8_0
DeepSeek R1 Distill Qwen 1.5B45tok/sQ8_0166tok/sQ8_0
MiniCPM5 2B31tok/sQ8_0114tok/sQ8_0
Spark X2.5 4B31tok/smlx-4bit113tok/smlx-4bit
FrogNano 4B 260928tok/sQ6_K92tok/sQ8_0
LFM2.5 2.6B27tok/sQ6_K91tok/sQ8_0
LFM2.5 VL 3B27tok/sQ6_K91tok/sQ8_0
Mellum2.1 12B A2.5B Thinkingoffload103tok/sQ8_0
granite vision 4.1 4boffload70tok/sQ8_0
granite 4.2 3boffload68tok/sQ8_0
DeepSeek R1 Distill Qwen 7Boffload53tok/sQ8_0
Kimi VL A3B Thinking 2506offload73tok/sQ8_0
GLM 4.6V Flashoffload49tok/sQ8_0
Ministral 3 3B Instruct 2512offload59tok/sQ8_0
Kimi VL A3Boffload71tok/smlx-8bit
GLM 4 9B 0414offload57tok/smlx-5bit
LFM2.5 24B A2Boffload54tok/sQ5_K_M
DeepSeek R1 Distill Llama 8Boffload37tok/sQ8_0
GLM 4.1V 9B Thinkingoffload43tok/smlx-8bit
Ministral 3 8B Reasoning 2512offload34tok/sQ8_0
Muse Glimmer 30Boffload30tok/sQ5_K_M
Ministral 3 14B Reasoning 2512offload29tok/sQ6_K
DeepSeek R1 Distill Qwen 14Boffload27tok/sQ5_K_M
Qwen 3.5 122B-A10Bwon't runoffload
Gemma 4 31Boffloadoffload
Qwen3 Coder Nextwon't runoffload
Mistral Small 4 119Bwon't runoffload
Devstral Small 2 24Boffloadoffload
Qwen3 Next 80B-A3Bwon't runoffload
Kimi Linear 48B-A3Boffloadoffload
Qwen3 Coder 30B-A3Boffloadoffload
Qwen3 32Bwon't runoffload
Mistral Small 3.2 24Boffloadoffload
DeepSeek R1 Distill Qwen 32Bwon't runoffload
Devstral Small 2507offloadoffload
Magistral Small 2506offloadoffload
Magistral Small 2507offloadoffload
Magistral Small 2509offloadoffload
Qwen3.8 27B OBLITERATEDoffloadoffload
granite 4.2 30bwon'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
Nemotron 3 Super 120B-A12Bwon't runwon't run
gpt-oss 120Bwon't runwon't run
GLM 4.5 Airwon'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 4060 or the NVIDIA GeForce RTX 4090?
Choose the NVIDIA GeForce RTX 4090 to run bigger models. Choose the NVIDIA GeForce RTX 4090 for speed. Choose the NVIDIA GeForce RTX 4060 to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 4060 or the NVIDIA GeForce RTX 4090?
At 64k context the NVIDIA GeForce RTX 4090 runs 49 of the models we track fully in memory and the NVIDIA GeForce RTX 4060 11; only the NVIDIA GeForce RTX 4090 holds Qwen 3.8 27B.
Which is faster for local AI, the NVIDIA GeForce RTX 4060 or the NVIDIA GeForce RTX 4090?
On the models both run fully in memory, the NVIDIA GeForce RTX 4090 is about 3.7× as fast as the NVIDIA GeForce RTX 4060 (estimated, median across models).
What is the price difference between the NVIDIA GeForce RTX 4060 and the NVIDIA GeForce RTX 4090?
In the US the NVIDIA GeForce RTX 4060 costs $530 at eBay and the NVIDIA GeForce RTX 4090 $2,073 at eBay: the NVIDIA GeForce RTX 4060 is $1,543 cheaper.

More comparisons

More hardware for local AI