🔌
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 Qwen2.5 Instruct (32B) 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 → | ~85.7 | yes | 37k | ~$1,999 |
| NVIDIA GeForce RTX 4090 → | ~48.2 | yes | 9k | ~$1,599 |
| NVIDIA GeForce RTX 3090 Ti → | ~48.2 | yes | 9k | ~$1,999 |
| NVIDIA GeForce RTX 3090 → | ~44.7 | yes | 9k | ~$1,499 |
| AMD Radeon RX 7900 XTX → | ~40.6 | yes | 9k | ~$999 |
| Intel Arc Pro B70 → | ~24.1 | yes | 37k | — |
| Intel Arc Pro B60 → | ~18 | yes | 9k | — |
| NVIDIA DGX Spark → | ~13.1 | yes | 364k | ~$3,999 |
| AMD Ryzen AI Max+ 395 → | ~10.8 | yes | 364k | ~$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 Qwen2.5 Instruct (32B)?▶
On GenAIList, 9 Consumer GPU options can run Qwen2.5 Instruct (32B) at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~85.7 tok/s.
How fast is Qwen2.5 Instruct (32B) on Consumer GPU hardware?▶
Estimated generation speed ranges from ~10.8 to ~85.7 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.