readygpu

NVIDIA GeForce RTX 4090 vs NVIDIA GeForce RTX 5060

For running models locally, priced in Germany. At 8k context the first runs 61 models fully in memory, the second 26.

In short

The NVIDIA GeForce RTX 4090 has more memory for models: 24 GB against 8 GB. At 8k context the NVIDIA GeForce RTX 4090 runs 61 of the models we track fully in memory and the NVIDIA GeForce RTX 5060 26; 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 2.2× as fast as the NVIDIA GeForce RTX 5060 (estimated, median across models). In Germany the NVIDIA GeForce RTX 4090 costs 4.385 € at eBay and the NVIDIA GeForce RTX 5060 449 € at eBay: the NVIDIA GeForce RTX 5060 is 3.936 € cheaper.

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

NVIDIA GeForce RTX 4090

4.385 €

eBay

Add to build
NVIDIA GeForce RTX 5060

449 €

eBay

Add to build

Specifications

SpecNVIDIA GeForce RTX 4090NVIDIA GeForce RTX 5060
GPUGeForce RTX 4090GeForce RTX 5060
Memory24 GB GDDR6X8 GB GDDR7
Memory bus384-bit128-bit
Memory bandwidth1,008 GB/s448 GB/s
FP16 compute165 TFLOPS19.177 TFLOPS
SoftwareCUDACUDA
Board power450 W145 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
Qwen 3.8 27B28tok/sUD-Q6_Koffload
Qwen 3.6 27B27tok/sQ6_Koffload
Gemma 4 31B27tok/sQ5_K_Moffload
Qwen 3.6 35B-A3B179tok/sQ4_K_Moffload
Qwen 3.5 27B27tok/sQ6_Koffload
Gemma 4 26B-A4B95tok/sUD-Q6_Koffload
Qwen 3.5 35B-A3B181tok/sQ4_K_Moffload
GLM 4.7 Flash94tok/sQ5_K_Moffload
Devstral Small 2 24B30tok/sQ6_Koffload
Nemotron 3.5 Lightning 30B-A3B163tok/sMXFP4offload
gpt-oss 20B142tok/sMXFP4offload
Qwen3 Coder 30B-A3B128tok/sQ5_K_Moffload
Qwen3 32B29tok/sQ4_K_Moffload
Gemma 4 12B48tok/sQ8_0offload
Qwen 3.5 9B64tok/sQ8_040tok/sQ5_K_M
Mistral Small 3.2 24B30tok/sQ6_Koffload
DeepSeek R1 Distill Qwen 32B28tok/sQ4_K_Moffload
Gemma 3 27B27tok/sQ6_Koffload
Ministral 3 14B40tok/sQ8_0offload
Qwen3 14B37tok/sQ8_0offload
DeepSeek R1 0528 Qwen3 8B63tok/sQ8_039tok/sQ5_K_M
Qwen3 8B63tok/sQ8_039tok/sQ5_K_M
Phi-4 14B36tok/sQ8_0offload
Qwen 3.5 4B130tok/sQ8_058tok/sQ8_0
Ministral 3 8B62tok/sQ8_044tok/sQ4_K_M
Granite 4.2 8B59tok/sQ8_040tok/sQ4_K_M
Gemma 4 E4B74tok/sQ8_048tok/sQ5_K_M
LFM2.5 8B-A1B256tok/sQ8_0144tok/sUD-Q5_K_M
Llama 3.1 8B82tok/sQ6_K41tok/sQ5_K_M
Qwen2.5 0.5B989tok/sQ8_0440tok/sQ8_0
Qwen3.5 0.8B671tok/sQ8_0298tok/sQ8_0
Qwen3.5 2B402tok/sQ5_K_M179tok/sQ5_K_M
LFM3 1.7B320tok/sQ8_0142tok/sQ8_0
DeepSeek R1 Distill Qwen 1.5B294tok/sQ8_0130tok/sQ8_0
MiniCPM5 2B206tok/sQ8_092tok/sQ8_0
LFM2.5 2.6B185tok/sQ8_082tok/sQ8_0
LFM2.5 VL 3B185tok/sQ8_082tok/sQ8_0
Spark X2.5 4B184tok/smlx-4bit82tok/smlx-4bit
LFM2.5 24B A2B154tok/sQ6_Koffload
granite vision 4.1 4b146tok/sQ8_065tok/sQ8_0
Ministral 3 3B Instruct 2512138tok/sQ8_061tok/sQ8_0
granite 4.2 3b137tok/sQ8_061tok/sQ8_0
Mellum2.1 12B A2.5B Thinking133tok/sQ8_0offload
FrogNano 4B 2609127tok/sQ8_056tok/sQ8_0
Kimi VL A3B Thinking 2506112tok/sQ8_0offload
Kimi VL A3B107tok/smlx-8bitoffload
DeepSeek R1 Distill Qwen 7B73tok/sQ8_041tok/sQ6_K
GLM 4 9B 041473tok/smlx-5bitoffload
DeepSeek R1 Distill Llama 8B65tok/sQ8_041tok/sQ5_K_M
Ministral 3 8B Reasoning 251262tok/sQ8_044tok/sQ4_K_M
GLM 4.6V Flash61tok/sQ8_043tok/sQ4_K_M
GLM 4.1V 9B Thinking52tok/smlx-8bitoffload
Ministral 3 14B Reasoning 251240tok/sQ8_0offload
DeepSeek R1 Distill Qwen 14B36tok/sQ8_0offload
Devstral Small 250735tok/sQ5_K_Moffload
Magistral Small 250735tok/sQ5_K_Moffload
Magistral Small 250935tok/sQ5_K_Moffload
Magistral Small 250630tok/sQ6_Koffload
Qwen3.8 27B OBLITERATED29tok/smlx-4bitoffload
granite 4.2 30b27tok/sQ5_K_Moffload
Muse Glimmer 30B27tok/sQ6_Koffload
Qwen 3.5 122B-A10Boffloadwon't run
Qwen3 Coder Nextoffloadwon't run
Mistral Small 4 119Boffloadwon't run
GLM 4.5 Airoffloadwon't run
Qwen3 Next 80B-A3Boffloadwon't run
Kimi Linear 48B-A3Boffloadoffload
Llama 3.3 70Boffloadwon't run
DeepSeek R1 Distill Llama 70Boffloadwon't run
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
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 4.5Vwon'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 4090 or the NVIDIA GeForce RTX 5060?
Choose the NVIDIA GeForce RTX 4090 to run bigger models. Choose the NVIDIA GeForce RTX 4090 for speed. Choose the NVIDIA GeForce RTX 5060 to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 4090 or the NVIDIA GeForce RTX 5060?
At 8k context the NVIDIA GeForce RTX 4090 runs 61 of the models we track fully in memory and the NVIDIA GeForce RTX 5060 26; 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?
On the models both run fully in memory, the NVIDIA GeForce RTX 4090 is about 2.2× as fast as the NVIDIA GeForce RTX 5060 (estimated, median across models).
What is the price difference between the NVIDIA GeForce RTX 4090 and the NVIDIA GeForce RTX 5060?
In Germany the NVIDIA GeForce RTX 4090 costs 4.385 € at eBay and the NVIDIA GeForce RTX 5060 449 € at eBay: the NVIDIA GeForce RTX 5060 is 3.936 € cheaper.

More comparisons

More hardware for local AI