🔌
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 DiffusionGemma 26B-A4B on Consumer GPU hardware
10 options ranked by estimated speed at Q4 / 8k context.
| Hardware | Est tok/s | Fits 8k? | Max ctx | ~Price |
|---|---|---|---|---|
| NVIDIA GeForce RTX 5090 → | ~107.1 | yes | 51k | ~$1,999 |
| NVIDIA GeForce RTX 4090 → | ~60.2 | yes | 23k | ~$1,599 |
| NVIDIA GeForce RTX 3090 Ti → | ~60.2 | yes | 23k | ~$1,999 |
| NVIDIA GeForce RTX 3090 → | ~55.9 | yes | 23k | ~$1,499 |
| AMD Radeon RX 7900 XTX → | ~50.8 | yes | 23k | ~$999 |
| AMD Radeon RX 7900 XT → | ~42.3 | yes | 9k | ~$899 |
| Intel Arc Pro B70 → | ~30.1 | yes | 51k | — |
| Intel Arc Pro B60 → | ~22.5 | yes | 23k | — |
| NVIDIA DGX Spark → | ~16.3 | yes | 378k | ~$3,999 |
| AMD Ryzen AI Max+ 395 → | ~13.5 | yes | 378k | ~$1,999 |
Estimate at Q4 (memory-bound). Click any option for its full per-hardware estimate and measured numbers.
FAQ
What Consumer GPU hardware runs DiffusionGemma 26B-A4B?▶
On GenAIList, 10 Consumer GPU options can run DiffusionGemma 26B-A4B at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~107.1 tok/s.
How fast is DiffusionGemma 26B-A4B on Consumer GPU hardware?▶
Estimated generation speed ranges from ~13.5 to ~107.1 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.