🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// RUN ON DATACENTER GPU
Run LLaVA-NeXT-34B (LLaVA-1.6) on Datacenter GPU hardware
13 options ranked by estimated speed at Q4 / 8k context.
| Hardware | Est tok/s | Fits 8k? | Max ctx | ~Price |
|---|---|---|---|---|
| NVIDIA B200 → | ~357.7 | yes | 594k | — |
| AMD Instinct MI325X → | ~237.4 | yes | 818k | — |
| NVIDIA H200 → | ~214.6 | yes | 415k | — |
| AMD Instinct MI300X 192GB → | ~209.7 | yes | 594k | ~$15,000 |
| NVIDIA H100 SXM5 80GB → | ~149.8 | yes | 201k | ~$30,000 |
| Intel Gaudi 3 → | ~136.9 | yes | 369k | — |
| NVIDIA A100 SXM4 80GB → | ~91.2 | yes | 201k | ~$15,000 |
| NVIDIA H100 PCIe 80GB → | ~89.4 | yes | 201k | ~$25,000 |
| NVIDIA A100 PCIe 80GB → | ~86.5 | yes | 201k | ~$12,000 |
| NVIDIA RTX PRO 6000 Blackwell → | ~80.1 | yes | 257k | ~$8,500 |
| NVIDIA RTX 6000 Ada 48GB → | ~42.9 | yes | 89k | ~$6,800 |
| NVIDIA L40S 48GB → | ~38.6 | yes | 89k | ~$10,000 |
| AMD Radeon Pro W7900 48GB → | ~34.2 | yes | 89k | ~$3,999 |
Estimate at Q4 (memory-bound). Click any option for its full per-hardware estimate and measured numbers.
FAQ
What Datacenter GPU hardware runs LLaVA-NeXT-34B (LLaVA-1.6)?▶
On GenAIList, 13 Datacenter GPU options can run LLaVA-NeXT-34B (LLaVA-1.6) at Q4 — the fastest is the NVIDIA B200 at ~357.7 tok/s.
How fast is LLaVA-NeXT-34B (LLaVA-1.6) on Datacenter GPU hardware?▶
Estimated generation speed ranges from ~34.2 to ~357.7 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.