🔌
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 InternVL2 26B 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 → | ~109.2 | yes | 52k | ~$1,999 |
| NVIDIA GeForce RTX 4090 → | ~61.4 | yes | 24k | ~$1,599 |
| NVIDIA GeForce RTX 3090 Ti → | ~61.4 | yes | 24k | ~$1,999 |
| NVIDIA GeForce RTX 3090 → | ~57 | yes | 24k | ~$1,499 |
| AMD Radeon RX 7900 XTX → | ~51.8 | yes | 24k | ~$999 |
| AMD Radeon RX 7900 XT → | ~43.1 | yes | 10k | ~$899 |
| Intel Arc Pro B70 → | ~30.7 | yes | 52k | — |
| Intel Arc Pro B60 → | ~23 | yes | 24k | — |
| NVIDIA DGX Spark → | ~16.6 | yes | 379k | ~$3,999 |
| AMD Ryzen AI Max+ 395 → | ~13.8 | yes | 379k | ~$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 InternVL2 26B?▶
On GenAIList, 10 Consumer GPU options can run InternVL2 26B at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~109.2 tok/s.
How fast is InternVL2 26B on Consumer GPU hardware?▶
Estimated generation speed ranges from ~13.8 to ~109.2 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.