🔌
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 C2S-Scale 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 → | ~103.1 | yes | 49k | ~$1,999 |
| NVIDIA GeForce RTX 4090 → | ~58 | yes | 21k | ~$1,599 |
| NVIDIA GeForce RTX 3090 Ti → | ~58 | yes | 21k | ~$1,999 |
| NVIDIA GeForce RTX 3090 → | ~53.9 | yes | 21k | ~$1,499 |
| AMD Radeon RX 7900 XTX → | ~48.9 | yes | 21k | ~$999 |
| AMD Radeon RX 7900 XT → | ~40.7 | tight | 7k | ~$899 |
| Intel Arc Pro B70 → | ~29 | yes | 49k | — |
| Intel Arc Pro B60 → | ~21.7 | yes | 21k | — |
| NVIDIA DGX Spark → | ~15.7 | yes | 376k | ~$3,999 |
| AMD Ryzen AI Max+ 395 → | ~13 | yes | 376k | ~$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 C2S-Scale?▶
On GenAIList, 10 Consumer GPU options can run C2S-Scale at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~103.1 tok/s.
How fast is C2S-Scale on Consumer GPU hardware?▶
Estimated generation speed ranges from ~13 to ~103.1 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.