🔌
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 Aquila2 34B on Consumer GPU hardware
9 options ranked by estimated speed at Q4 / 8k context.
| Hardware | Est tok/s | Fits 8k? | Max ctx | ~Price |
|---|---|---|---|---|
| NVIDIA GeForce RTX 5090 → | ~81.9 | yes | 34k | ~$1,999 |
| NVIDIA GeForce RTX 4090 → | ~46.1 | tight | 6k | ~$1,599 |
| NVIDIA GeForce RTX 3090 Ti → | ~46.1 | tight | 6k | ~$1,999 |
| NVIDIA GeForce RTX 3090 → | ~42.8 | tight | 6k | ~$1,499 |
| AMD Radeon RX 7900 XTX → | ~38.8 | tight | 6k | ~$999 |
| Intel Arc Pro B70 → | ~23 | yes | 34k | — |
| Intel Arc Pro B60 → | ~17.2 | tight | 6k | — |
| NVIDIA DGX Spark → | ~12.5 | yes | 361k | ~$3,999 |
| AMD Ryzen AI Max+ 395 → | ~10.4 | yes | 361k | ~$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 Aquila2 34B?▶
On GenAIList, 9 Consumer GPU options can run Aquila2 34B at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~81.9 tok/s.
How fast is Aquila2 34B on Consumer GPU hardware?▶
Estimated generation speed ranges from ~10.4 to ~81.9 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.