🔌
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 TinyBert 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 → | ~41,552.2 | yes | 426k | ~$1,999 |
| NVIDIA GeForce RTX 4090 → | ~23,373.1 | yes | 313k | ~$1,599 |
| NVIDIA GeForce RTX 3090 Ti → | ~23,373.1 | yes | 313k | ~$1,999 |
| NVIDIA GeForce RTX 5080 → | ~22,260.1 | yes | 201k | ~$999 |
| NVIDIA GeForce RTX 3090 → | ~21,703.6 | yes | 313k | ~$1,499 |
| NVIDIA GeForce RTX 3080 Ti → | ~21,147.1 | yes | 145k | ~$1,199 |
| NVIDIA GeForce RTX 5070 Ti → | ~20,776.1 | yes | 201k | ~$749 |
| AMD Radeon RX 7900 XTX → | ~19,701.5 | yes | 313k | ~$999 |
| NVIDIA GeForce RTX 3080 10GB → | ~17,622.6 | yes | 117k | ~$699 |
| NVIDIA GeForce RTX 4080 → | ~17,066.1 | yes | 201k | ~$1,199 |
| AMD Radeon RX 7900 XT → | ~16,417.9 | yes | 257k | ~$899 |
| NVIDIA GeForce RTX 5070 → | ~15,582.1 | yes | 145k | ~$549 |
| NVIDIA GeForce RTX 4070 Ti Super → | ~15,582.1 | yes | 201k | ~$799 |
| NVIDIA GeForce RTX 3070 Ti → | ~14,098.1 | yes | 89k | ~$599 |
| AMD Radeon RX 9070 XT → | ~13,216.4 | yes | 201k | ~$599 |
| AMD Radeon RX 7800 XT → | ~12,806 | yes | 201k | ~$499 |
| NVIDIA GeForce RTX 4070 Super → | ~11,686.6 | yes | 145k | ~$599 |
| NVIDIA GeForce RTX 4070 → | ~11,686.6 | yes | 145k | ~$599 |
| Intel Arc Pro B70 → | ~11,667.4 | yes | 426k | — |
| Intel Arc A770 16GB → | ~10,746.3 | yes | 201k | ~$329 |
| AMD Radeon RX 6800 XT → | ~10,507.5 | yes | 201k | ~$649 |
| AMD Radeon RX 6900 XT → | ~10,507.5 | yes | 201k | ~$999 |
| NVIDIA GeForce RTX 3070 → | ~10,388.1 | yes | 89k | ~$499 |
| NVIDIA GeForce RTX 5060 Ti 16GB → | ~10,388.1 | yes | 201k | ~$429 |
| NVIDIA GeForce RTX 5060 Ti 8GB → | ~10,388.1 | yes | 89k | ~$379 |
| Intel Arc Pro B60 → | ~8,750.5 | yes | 313k | — |
| Intel Arc B580 12GB → | ~8,750.5 | yes | 145k | ~$249 |
| NVIDIA GeForce RTX 4060 Ti 8GB → | ~6,678 | yes | 89k | ~$399 |
| NVIDIA GeForce RTX 4060 Ti 16GB → | ~6,678 | yes | 201k | ~$499 |
| NVIDIA DGX Spark → | ~6,330.2 | yes | 1734k | ~$3,999 |
| AMD Ryzen AI Max+ 395 → | ~5,253.7 | yes | 1734k | ~$1,999 |
| Intel Arc Pro B50 → | ~4,298.5 | yes | 201k | — |
| NVIDIA GeForce RTX 2050 Mobile → | ~2,597 | yes | 33k | — |
Estimate at Q4 (memory-bound). Click any option for its full per-hardware estimate and measured numbers.
FAQ
What Consumer GPU hardware runs TinyBert?▶
On GenAIList, 33 Consumer GPU options can run TinyBert at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~41,552.2 tok/s.
How fast is TinyBert on Consumer GPU hardware?▶
Estimated generation speed ranges from ~2,597 to ~41,552.2 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.