Arc A770 vs Arc B580 for local AI
The Arc A770 fits more: up to gpt-oss 20B, against Qwen3 14B on the Arc B580. The Arc A770 generates about 23% faster on any model both can run, because it has 560 GB/s of memory bandwidth to the Arc B580's 456 GB/s.
Memory and bandwidth
Memory decides which models fit. Bandwidth decides how fast they generate, because every token reads the model's active weights once.
| Arc A770 | Arc B580 | |
|---|---|---|
| Memory | 8 or 16 GB VRAM | 12 GB VRAM |
| Bandwidth | 560 GB/s | 456 GB/s |
| Biggest model that fits | gpt-oss 20B | Qwen3 14B |
| Best everyday pick | gpt-oss 20B, ~98 tok/s | Qwen3 14B, ~27 tok/s |
Every model, side by side
Estimated generation speed at the largest memory size each was sold in (16 GB and 12 GB).
| Model | Arc A770 | Arc B580 |
|---|---|---|
| Qwen3 4B About 4 GB | ~120 tok/s Runs great | ~100 tok/s Runs great |
| Qwen3 8B About 7 GB | ~59 tok/s Runs great | ~48 tok/s Runs great |
| Gemma 3 12B About 10 GB | ~38 tok/s Runs great | ~31 tok/s Runs great |
| Qwen3 14B About 11 GB | ~33 tok/s Runs great | ~27 tok/s Usable |
| gpt-oss 20B About 16 GB | ~98 tok/s Runs great | Needs 16 GB |
| Gemma 3 27B About 19 GB | Needs 19 GB | Needs 19 GB |
| Qwen3 30B-A3B About 21 GB | Needs 21 GB | Needs 21 GB |
| Qwen3 32B About 22 GB | Needs 22 GB | Needs 22 GB |
| Llama 3.3 70B About 45 GB | Needs 45 GB | Needs 45 GB |
| gpt-oss 120B About 67 GB | Needs 67 GB | Needs 67 GB |
| Qwen3 235B-A22B About 144 GB | Needs 144 GB | Needs 144 GB |
| DeepSeek R1 671B About 406 GB | Needs 406 GB | Needs 406 GB |
The Arc A770: it fits bigger models and runs faster. Price matters as much as either number: check used prices on the builds page, where every parts list has a measured or estimated speed.
Both columns use the same formula: memory bandwidth divided by the weights read per token, calibrated on our own rack, with Ollama's default 4-bit sizes. Real results are usually within about a third. Measured either one? Send us the number.