🔌
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 GPT-2 (124M) 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 → | ~22,451.6 | yes | 425k | ~$1,999 |
| NVIDIA GeForce RTX 4090 → | ~12,629 | yes | 313k | ~$1,599 |
| NVIDIA GeForce RTX 3090 Ti → | ~12,629 | yes | 313k | ~$1,999 |
| NVIDIA GeForce RTX 5080 → | ~12,027.6 | yes | 201k | ~$999 |
| NVIDIA GeForce RTX 3090 → | ~11,727 | yes | 313k | ~$1,499 |
| NVIDIA GeForce RTX 3080 Ti → | ~11,426.3 | yes | 145k | ~$1,199 |
| NVIDIA GeForce RTX 5070 Ti → | ~11,225.8 | yes | 201k | ~$749 |
| AMD Radeon RX 7900 XTX → | ~10,645.2 | yes | 313k | ~$999 |
| NVIDIA GeForce RTX 3080 10GB → | ~9,521.9 | yes | 116k | ~$699 |
| NVIDIA GeForce RTX 4080 → | ~9,221.2 | yes | 201k | ~$1,199 |
| AMD Radeon RX 7900 XT → | ~8,871 | yes | 257k | ~$899 |
| NVIDIA GeForce RTX 5070 → | ~8,419.4 | yes | 145k | ~$549 |
| NVIDIA GeForce RTX 4070 Ti Super → | ~8,419.4 | yes | 201k | ~$799 |
| NVIDIA GeForce RTX 3070 Ti → | ~7,617.5 | yes | 88k | ~$599 |
| AMD Radeon RX 9070 XT → | ~7,141.1 | yes | 201k | ~$599 |
| AMD Radeon RX 7800 XT → | ~6,919.4 | yes | 201k | ~$499 |
| NVIDIA GeForce RTX 4070 Super → | ~6,314.5 | yes | 145k | ~$599 |
| NVIDIA GeForce RTX 4070 → | ~6,314.5 | yes | 145k | ~$599 |
| Intel Arc Pro B70 → | ~6,304.1 | yes | 425k | — |
| Intel Arc A770 16GB → | ~5,806.5 | yes | 201k | ~$329 |
| AMD Radeon RX 6800 XT → | ~5,677.4 | yes | 201k | ~$649 |
| AMD Radeon RX 6900 XT → | ~5,677.4 | yes | 201k | ~$999 |
| NVIDIA GeForce RTX 3070 → | ~5,612.9 | yes | 88k | ~$499 |
| NVIDIA GeForce RTX 5060 Ti 16GB → | ~5,612.9 | yes | 201k | ~$429 |
| NVIDIA GeForce RTX 5060 Ti 8GB → | ~5,612.9 | yes | 88k | ~$379 |
| Intel Arc Pro B60 → | ~4,728.1 | yes | 313k | — |
| Intel Arc B580 12GB → | ~4,728.1 | yes | 145k | ~$249 |
| NVIDIA GeForce RTX 4060 Ti 8GB → | ~3,608.3 | yes | 88k | ~$399 |
| NVIDIA GeForce RTX 4060 Ti 16GB → | ~3,608.3 | yes | 201k | ~$499 |
| NVIDIA DGX Spark → | ~3,420.4 | yes | 1734k | ~$3,999 |
| AMD Ryzen AI Max+ 395 → | ~2,838.7 | yes | 1734k | ~$1,999 |
| Intel Arc Pro B50 → | ~2,322.6 | yes | 201k | — |
| NVIDIA GeForce RTX 2050 Mobile → | ~1,403.2 | yes | 32k | — |
Estimate at Q4 (memory-bound). Click any option for its full per-hardware estimate and measured numbers.
FAQ
What Consumer GPU hardware runs GPT-2 (124M)?▶
On GenAIList, 33 Consumer GPU options can run GPT-2 (124M) at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~22,451.6 tok/s.
How fast is GPT-2 (124M) on Consumer GPU hardware?▶
Estimated generation speed ranges from ~1,403.2 to ~22,451.6 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.