🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// RUN ON CONSUMER GPU
Run BERT-Large on Consumer GPU hardware
33 options ranked by estimated speed at Q4 / 8k context.
| Hardware | Est tok/s | Fits 8k? | Max ctx | ~Price |
|---|---|---|---|---|
| NVIDIA GeForce RTX 5090 → | ~8,188.2 | yes | 423k | ~$1,999 |
| NVIDIA GeForce RTX 4090 → | ~4,605.9 | yes | 311k | ~$1,599 |
| NVIDIA GeForce RTX 3090 Ti → | ~4,605.9 | yes | 311k | ~$1,999 |
| NVIDIA GeForce RTX 5080 → | ~4,386.6 | yes | 199k | ~$999 |
| NVIDIA GeForce RTX 3090 → | ~4,276.9 | yes | 311k | ~$1,499 |
| NVIDIA GeForce RTX 3080 Ti → | ~4,167.2 | yes | 143k | ~$1,199 |
| NVIDIA GeForce RTX 5070 Ti → | ~4,094.1 | yes | 199k | ~$749 |
| AMD Radeon RX 7900 XTX → | ~3,882.4 | yes | 311k | ~$999 |
| NVIDIA GeForce RTX 3080 10GB → | ~3,472.7 | yes | 115k | ~$699 |
| NVIDIA GeForce RTX 4080 → | ~3,363 | yes | 199k | ~$1,199 |
| AMD Radeon RX 7900 XT → | ~3,235.3 | yes | 255k | ~$899 |
| NVIDIA GeForce RTX 5070 → | ~3,070.6 | yes | 143k | ~$549 |
| NVIDIA GeForce RTX 4070 Ti Super → | ~3,070.6 | yes | 199k | ~$799 |
| NVIDIA GeForce RTX 3070 Ti → | ~2,778.2 | yes | 87k | ~$599 |
| AMD Radeon RX 9070 XT → | ~2,604.4 | yes | 199k | ~$599 |
| AMD Radeon RX 7800 XT → | ~2,523.5 | yes | 199k | ~$499 |
| NVIDIA GeForce RTX 4070 Super → | ~2,302.9 | yes | 143k | ~$599 |
| NVIDIA GeForce RTX 4070 → | ~2,302.9 | yes | 143k | ~$599 |
| Intel Arc Pro B70 → | ~2,299.2 | yes | 423k | — |
| Intel Arc A770 16GB → | ~2,117.6 | yes | 199k | ~$329 |
| AMD Radeon RX 6800 XT → | ~2,070.6 | yes | 199k | ~$649 |
| AMD Radeon RX 6900 XT → | ~2,070.6 | yes | 199k | ~$999 |
| NVIDIA GeForce RTX 3070 → | ~2,047.1 | yes | 87k | ~$499 |
| NVIDIA GeForce RTX 5060 Ti 16GB → | ~2,047.1 | yes | 199k | ~$429 |
| NVIDIA GeForce RTX 5060 Ti 8GB → | ~2,047.1 | yes | 87k | ~$379 |
| Intel Arc Pro B60 → | ~1,724.4 | yes | 311k | — |
| Intel Arc B580 12GB → | ~1,724.4 | yes | 143k | ~$249 |
| NVIDIA GeForce RTX 4060 Ti 8GB → | ~1,316 | yes | 87k | ~$399 |
| NVIDIA GeForce RTX 4060 Ti 16GB → | ~1,316 | yes | 199k | ~$499 |
| NVIDIA DGX Spark → | ~1,247.4 | yes | 1732k | ~$3,999 |
| AMD Ryzen AI Max+ 395 → | ~1,035.3 | yes | 1732k | ~$1,999 |
| Intel Arc Pro B50 → | ~847.1 | yes | 199k | — |
| NVIDIA GeForce RTX 2050 Mobile → | ~511.8 | yes | 30k | — |
Estimate at Q4 (memory-bound). Click any option for its full per-hardware estimate and measured numbers.
FAQ
What Consumer GPU hardware runs BERT-Large?▶
On GenAIList, 33 Consumer GPU options can run BERT-Large at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~8,188.2 tok/s.
How fast is BERT-Large on Consumer GPU hardware?▶
Estimated generation speed ranges from ~511.8 to ~8,188.2 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.