L4 vs Arc Pro B60 for local AI
Both fit the same models we track, up to Qwen3 32B. The Arc Pro B60 generates about 52% faster on any model both can run, because it has 456 GB/s of memory bandwidth to the L4's 300 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.
| L4 | Arc Pro B60 | |
|---|---|---|
| Memory | 24 GB VRAM | 24 GB VRAM |
| Bandwidth | 300 GB/s | 456 GB/s |
| Biggest model that fits | Qwen3 32B | Qwen3 32B |
| Best everyday pick | Qwen3 30B-A3B, ~53 tok/s | Qwen3 30B-A3B, ~80 tok/s |
Every model, side by side
Estimated generation speed at the largest memory size each was sold in (24 GB and 24 GB).
| Model | L4 | Arc Pro B60 |
|---|---|---|
| Qwen3 4B About 4 GB | ~66 tok/s Runs great | ~100 tok/s Runs great |
| Qwen3 8B About 7 GB | ~32 tok/s Runs great | ~48 tok/s Runs great |
| Gemma 3 12B About 10 GB | ~20 tok/s Usable | ~31 tok/s Runs great |
| Qwen3 14B About 11 GB | ~18 tok/s Usable | ~27 tok/s Usable |
| gpt-oss 20B About 16 GB | ~53 tok/s Runs great | ~80 tok/s Runs great |
| Gemma 3 27B About 19 GB | ~10 tok/s Slow | ~15 tok/s Usable |
| Qwen3 30B-A3B About 21 GB | ~53 tok/s Runs great | ~80 tok/s Runs great |
| Qwen3 32B About 22 GB | ~8 tok/s Slow | ~13 tok/s Usable |
| 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 Pro B60, for speed. They fit the same models. 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.