🔌
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-sw3-40b on Consumer GPU hardware
4 options ranked by estimated speed at Q4 / 8k context.
| Hardware | Est tok/s | Fits 8k? | Max ctx | ~Price |
|---|---|---|---|---|
| NVIDIA GeForce RTX 5090 → | ~69.6 | yes | 17k | ~$1,999 |
| Intel Arc Pro B70 → | ~19.5 | yes | 17k | — |
| NVIDIA DGX Spark → | ~10.6 | yes | 279k | ~$3,999 |
| AMD Ryzen AI Max+ 395 → | ~8.8 | yes | 279k | ~$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 gpt-sw3-40b?▶
On GenAIList, 4 Consumer GPU options can run gpt-sw3-40b at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~69.6 tok/s.
How fast is gpt-sw3-40b on Consumer GPU hardware?▶
Estimated generation speed ranges from ~8.8 to ~69.6 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.