🔌
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 LLaVA-NeXT-34B (LLaVA-1.6) 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 → | ~80.1 | yes | 32k | ~$1,999 |
| NVIDIA GeForce RTX 4090 → | ~45.1 | tight | 4k | ~$1,599 |
| NVIDIA GeForce RTX 3090 Ti → | ~45.1 | tight | 4k | ~$1,999 |
| NVIDIA GeForce RTX 3090 → | ~41.8 | tight | 4k | ~$1,499 |
| AMD Radeon RX 7900 XTX → | ~38 | tight | 4k | ~$999 |
| Intel Arc Pro B70 → | ~22.5 | yes | 32k | — |
| Intel Arc Pro B60 → | ~16.9 | tight | 4k | — |
| NVIDIA DGX Spark → | ~12.2 | yes | 359k | ~$3,999 |
| AMD Ryzen AI Max+ 395 → | ~10.1 | yes | 359k | ~$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 LLaVA-NeXT-34B (LLaVA-1.6)?▶
On GenAIList, 9 Consumer GPU options can run LLaVA-NeXT-34B (LLaVA-1.6) at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~80.1 tok/s.
How fast is LLaVA-NeXT-34B (LLaVA-1.6) on Consumer GPU hardware?▶
Estimated generation speed ranges from ~10.1 to ~80.1 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.