NVIDIA GeForce RTX 3090 vs NVIDIA GeForce RTX 5060
For running models locally, priced in the US. At 128k context the first runs 32 models fully in memory, the second 5.
In short
The NVIDIA GeForce RTX 3090 has more memory for models: 24 GB against 8 GB. At 128k context the NVIDIA GeForce RTX 3090 runs 32 of the models we track fully in memory and the NVIDIA GeForce RTX 5060 5; only the NVIDIA GeForce RTX 3090 holds Gemma 4 26B-A4B. On the models both run fully in memory, the NVIDIA GeForce RTX 3090 is about 2.1× as fast as the NVIDIA GeForce RTX 5060 (estimated, median across models). In the US the NVIDIA GeForce RTX 3090 costs $1,698 at Amazon and the NVIDIA GeForce RTX 5060 $475 at eBay: the NVIDIA GeForce RTX 5060 is $1,223 cheaper.
Updated . Speeds are estimates; how they are worked out.
Specifications
| Spec | NVIDIA GeForce RTX 3090 | NVIDIA GeForce RTX 5060 |
|---|---|---|
| GPU | GeForce RTX 3090 | GeForce RTX 5060 |
| Memory | 24 GB GDDR6X | 8 GB GDDR7 |
| Memory bus | 384-bit | 128-bit |
| Memory bandwidth | 936 GB/s | 448 GB/s |
| FP16 compute | 71 TFLOPS | 19.177 TFLOPS |
| Software | CUDA | CUDA |
| Board power | 350 W | 145 W |
| PCIe generation | Gen 4 | Gen 5 |
| PCIe lanes | x16 | x8 |
What each runs
Estimated decode speed with the most precise quant that fits each one est.
| Model | NVIDIA GeForce RTX 3090 | NVIDIA GeForce RTX 5060 |
|---|---|---|
| Gemma 4 26B-A4B | 59tok/sQ5_K_M | offload |
| gpt-oss 20B | 62tok/sMXFP4 | offload |
| Gemma 4 12B | 38tok/sQ8_0 | offload |
| Qwen 3.5 9B | 42tok/sQ8_0 | offload |
| Qwen 3.5 4B | 66tok/sQ8_0 | offload |
| Ministral 3 8B | 25tok/sQ4_K_M | offload |
| Gemma 4 E4B | 48tok/sQ8_0 | offload |
| LFM2.5 8B-A1B | 46tok/sQ8_0 | offload |
| Llama 3.1 8B | 25tok/sQ5_K_M | offload |
| Qwen2.5 0.5B | 271tok/sQ8_0 | 130tok/sQ8_0 |
| Qwen3.5 0.8B | 238tok/sQ8_0 | 114tok/sQ8_0 |
| Qwen3.5 2B | 189tok/sQ5_K_M | 91tok/sQ5_K_M |
| LFM3 1.7B | 167tok/sQ8_0 | 80tok/sQ8_0 |
| DeepSeek R1 Distill Qwen 1.5B | 103tok/sQ8_0 | 49tok/sQ8_0 |
| Mellum2.1 12B A2.5B Thinking | 76tok/sQ8_0 | offload |
| Spark X2.5 4B | 73tok/smlx-4bit | offload |
| MiniCPM5 2B | 70tok/sQ8_0 | offload |
| FrogNano 4B 2609 | 65tok/sQ8_0 | offload |
| LFM2.5 2.6B | 53tok/sQ8_0 | offload |
| LFM2.5 VL 3B | 53tok/sQ8_0 | offload |
| Kimi VL A3B Thinking 2506 | 49tok/sQ8_0 | offload |
| Kimi VL A3B | 48tok/smlx-8bit | offload |
| GLM 4 9B 0414 | 43tok/smlx-5bit | offload |
| granite vision 4.1 4b | 40tok/sQ8_0 | offload |
| granite 4.2 3b | 40tok/sQ8_0 | offload |
| GLM 4.6V Flash | 38tok/sQ8_0 | offload |
| DeepSeek R1 Distill Qwen 7B | 37tok/sQ8_0 | offload |
| GLM 4.1V 9B Thinking | 34tok/smlx-8bit | offload |
| Ministral 3 3B Instruct 2512 | 33tok/sQ8_0 | offload |
| Muse Glimmer 30B | 27tok/sQ5_K_M | offload |
| DeepSeek R1 Distill Llama 8B | 25tok/sQ5_K_M | offload |
| Ministral 3 8B Reasoning 2512 | 25tok/sQ4_K_M | offload |
| Qwen 3.8 27B | offload | offload |
| Qwen 3.5 122B-A10B | offload | won't run |
| Qwen 3.6 27B | offload | offload |
| Gemma 4 31B | offload | offload |
| Mistral Small 4 119B | offload | won't run |
| Qwen 3.6 35B-A3B | offload | offload |
| Qwen 3.5 27B | offload | offload |
| Qwen 3.5 35B-A3B | offload | offload |
| GLM 4.7 Flash | offload | offload |
| Devstral Small 2 24B | offload | won't run |
| Nemotron 3.5 Lightning 30B-A3B | offload | offload |
| Kimi Linear 48B-A3B | offload | offload |
| Qwen3 Coder 30B-A3B | offload | offload |
| Gemma 3 27B | offload | offload |
| Mistral Small 3.2 24B | offload | won't run |
| Ministral 3 14B | offload | offload |
| Qwen3 14B | offload | offload |
| DeepSeek R1 0528 Qwen3 8B | offload | offload |
| Qwen3 8B | offload | offload |
| Phi-4 14B | offload | won't run |
| Granite 4.2 8B | offload | offload |
| LFM2.5 24B A2B | offload | offload |
| Qwen3.8 27B OBLITERATED | offload | offload |
| Ministral 3 14B Reasoning 2512 | offload | offload |
| DeepSeek R1 Distill Qwen 14B | offload | won't run |
| Devstral Small 2507 | offload | won't run |
| Magistral Small 2506 | offload | won't run |
| Magistral Small 2507 | offload | won't run |
| Magistral Small 2509 | offload | won't run |
| DeepSeek V4 Flash | won't run | won't run |
| GLM 5.3 Flash | won't run | won't run |
| Qwen 3.8 Flash Next | won't run | won't run |
| MiniMax M2.7 | won't run | won't run |
| Nemotron 3 Super 120B-A12B | won't run | won't run |
| Qwen3 Coder Next | won't run | won't run |
| gpt-oss 120B | won't run | won't run |
| GLM 4.5 Air | won't run | won't run |
| Qwen3 Next 80B-A3B | won't run | won't run |
| Qwen3 32B | won't run | won't run |
| DeepSeek R1 Distill Qwen 32B | won't run | won't run |
| Llama 3.3 70B | won't run | won't run |
| DeepSeek R1 | won't run | won't run |
| DeepSeek R1 0528 | won't run | won't run |
| DeepSeek R1 Distill Llama 70B | won't run | won't run |
| DeepSeek R1 Zero | won't run | won't run |
| DeepSeek V3 | won't run | won't run |
| DeepSeek V3 0324 | won't run | won't run |
| DeepSeek V3.1 | won't run | won't run |
| DeepSeek V3.1 Terminus | won't run | won't run |
| DeepSeek V3.2 | won't run | won't run |
| DeepSeek V4 Flash 0731 | won't run | won't run |
| DeepSeek V4 Flash Vision Exp | won't run | won't run |
| Devstral 2 123B Instruct 2512 | won't run | won't run |
| GLM 4.5 | won't run | won't run |
| GLM 4.5V | won't run | won't run |
| GLM 4.6 | won't run | won't run |
| GLM 4.6V | won't run | won't run |
| GLM 4.7 | won't run | won't run |
| GLM 5 | won't run | won't run |
| GLM 5.1 | won't run | won't run |
| GLM 5.2 | won't run | won't run |
| GLM 5.3 | won't run | won't run |
| Kimi Dev 72B | won't run | won't run |
| Kimi K2 | won't run | won't run |
| Kimi K2 Instruct 0905 | won't run | won't run |
| Kimi K2 Thinking | won't run | won't run |
| Kimi K2.5 | won't run | won't run |
| MiniMax M2 | won't run | won't run |
| MiniMax M2.1 | won't run | won't run |
| MiniMax M2.5 | won't run | won't run |
| MiniMax M3 | won't run | won't run |
| Mistral Medium 3.5 128B | won't run | won't run |
| granite 4.2 30b | won't run | won't run |
Questions
- Which is better for local AI, the NVIDIA GeForce RTX 3090 or the NVIDIA GeForce RTX 5060?
- Choose the NVIDIA GeForce RTX 3090 to run bigger models. Choose the NVIDIA GeForce RTX 3090 for speed. Choose the NVIDIA GeForce RTX 5060 to spend less.
- Which can run bigger models, the NVIDIA GeForce RTX 3090 or the NVIDIA GeForce RTX 5060?
- At 128k context the NVIDIA GeForce RTX 3090 runs 32 of the models we track fully in memory and the NVIDIA GeForce RTX 5060 5; only the NVIDIA GeForce RTX 3090 holds Gemma 4 26B-A4B.
- Which is faster for local AI, the NVIDIA GeForce RTX 3090 or the NVIDIA GeForce RTX 5060?
- On the models both run fully in memory, the NVIDIA GeForce RTX 3090 is about 2.1× as fast as the NVIDIA GeForce RTX 5060 (estimated, median across models).
- What is the price difference between the NVIDIA GeForce RTX 3090 and the NVIDIA GeForce RTX 5060?
- In the US the NVIDIA GeForce RTX 3090 costs $1,698 at Amazon and the NVIDIA GeForce RTX 5060 $475 at eBay: the NVIDIA GeForce RTX 5060 is $1,223 cheaper.
More comparisons
- Mac mini M4 16GB vs NVIDIA GeForce RTX 5060
- Mac mini M4 Pro 48GB vs NVIDIA GeForce RTX 3090
- NVIDIA GeForce RTX 3080 10GB vs NVIDIA GeForce RTX 5060
- NVIDIA GeForce RTX 3090 vs NVIDIA GeForce RTX 3090 Ti
- NVIDIA GeForce RTX 3090 vs NVIDIA GeForce RTX 5070 Ti
- NVIDIA GeForce RTX 3090 vs NVIDIA GeForce RTX 5080
- NVIDIA GeForce RTX 3090 vs NVIDIA RTX PRO 4000 Blackwell
- NVIDIA GeForce RTX 3090 vs NVIDIA RTX PRO 4500 Blackwell
- NVIDIA GeForce RTX 3090 vs AMD Radeon RX 7900 XTX
- NVIDIA GeForce RTX 4060 Ti 8GB vs NVIDIA GeForce RTX 5060