Intel Arc B580 vs NVIDIA GeForce RTX 3060 12GB
For running models locally, priced in India. At 8k context the first runs 13 models fully in memory, the second 13.
In short
Both have 12 GB of memory for models; the Intel Arc B580 has 456 GB/s of bandwidth and the NVIDIA GeForce RTX 3060 12GB 360 GB/s. At 8k context both run the same 13 models we track fully in memory. On the models both run fully in memory, the Intel Arc B580 and the NVIDIA GeForce RTX 3060 12GB are about as fast as each other (estimated).
Updated . Speeds are estimates; how they are worked out.
Specifications
| Spec | Intel Arc B580 | NVIDIA GeForce RTX 3060 12GB |
|---|---|---|
| GPU | Arc B580 | GeForce RTX 3060 12GB |
| Memory | 12 GB GDDR6 | 12 GB GDDR6 |
| Memory bus | 192-bit | 192-bit |
| Memory bandwidth | 456 GB/s | 360 GB/s |
| FP16 compute | 116.5 TFLOPS | 25.6 TFLOPS |
| Software | SYCL / oneAPI | CUDA |
| Board power | 190 W | 170 W |
| PCIe generation | Gen 4 | Gen 4 |
| PCIe lanes | x8 | x16 |
What each runs
Estimated decode speed with the most precise quant that fits each one est.
| Model | Intel Arc B580 | NVIDIA GeForce RTX 3060 12GB |
|---|---|---|
| Gemma 4 12B | 22tok/sQ6_K | 22tok/sQ6_K |
| Qwen 3.5 9B | 23tok/sQ8_0 | 23tok/sQ8_0 |
| Qwen3 14B | 22tok/sQ4_K_M | 22tok/sQ4_K_M |
| Ministral 3 14B | 21tok/sQ5_K_M | 20tok/sQ5_K_M |
| DeepSeek R1 0528 Qwen3 8B | 23tok/sQ8_0 | 23tok/sQ8_0 |
| Qwen3 8B | 23tok/sQ8_0 | 23tok/sQ8_0 |
| Phi-4 14B | 22tok/sQ4_K_M | 21tok/sQ4_K_M |
| Qwen 3.5 4B | 48tok/sQ8_0 | 47tok/sQ8_0 |
| Ministral 3 8B | 22tok/sQ8_0 | 22tok/sQ8_0 |
| Granite 4.2 8B | 21tok/sQ8_0 | 21tok/sQ8_0 |
| Gemma 4 E4B | 27tok/sQ8_0 | 26tok/sQ8_0 |
| LFM2.5 8B-A1B | 86tok/sQ8_0 | 91tok/sQ8_0 |
| Llama 3.1 8B | 30tok/sQ6_K | 29tok/sQ6_K |
| Qwen 3.8 27B | offload | offload |
| Qwen 3.6 27B | offload | offload |
| Gemma 4 31B | offload | offload |
| Qwen 3.6 35B-A3B | offload | offload |
| Qwen 3.5 27B | offload | offload |
| Gemma 4 26B-A4B | offload | offload |
| Qwen 3.5 35B-A3B | offload | offload |
| GLM 4.7 Flash | offload | offload |
| Devstral Small 2 24B | offload | offload |
| Nemotron 3.5 Lightning 30B-A3B | offload | offload |
| gpt-oss 20B | offload | offload |
| Kimi Linear 48B-A3B | offload | offload |
| Qwen3 Coder 30B-A3B | offload | offload |
| Qwen3 32B | offload | offload |
| Mistral Small 3.2 24B | offload | offload |
| Gemma 3 27B | offload | offload |
| DeepSeek R1 Distill Qwen 32B | offload | offload |
| 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 |
| Qwen 3.5 122B-A10B | 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 |
| Mistral Small 4 119B | 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 |
| Llama 3.3 70B | won't run | won't run |
Questions
- Which can run bigger models, the Intel Arc B580 or the NVIDIA GeForce RTX 3060 12GB?
- At 8k context both run the same 13 models we track fully in memory.
- Which is faster for local AI, the Intel Arc B580 or the NVIDIA GeForce RTX 3060 12GB?
- On the models both run fully in memory, the Intel Arc B580 and the NVIDIA GeForce RTX 3060 12GB are about as fast as each other (estimated).