Can I Run Llama 3.2 Vision 90B on NVIDIA RTX PRO 6000 Blackwell?
Autor: Jakub Rusinowski · Ostatnia aktualizacja: 21 lipca 2026
Yes. Llama 3.2 Vision 90B needs 57.8 GB at 8K context (53.6 GB weights + 4.2 GB KV cache/overhead) at Q4_K_M and the NVIDIA RTX PRO 6000 Blackwell has 96 GB, leaving about 38.2 GB of headroom, at roughly 26 tok/s (estimated) with room for up to 64K of context.
See what else this hardware can run →
The numbers
| Model | Llama 3.2 Vision 90B |
| Parameters | 90B |
| Quantization | Q4_K_M |
| VRAM needed (8K context) | 57.8 GB |
| NVIDIA RTX PRO 6000 Blackwell VRAM | 96 GB |
| Verdict | Runs |
| Max context | 64K |
| Estimated speed | ~26 tok/s |
Llama 3.2 Vision 90B on the NVIDIA RTX PRO 6000 Blackwell: VRAM by quantization
| Quant | VRAM needed | Fits 96 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 181.8 GB | ✗ No | — | — |
| Q8_0 | 98.5 GB | ✗ No | — | — |
| Q6_K | 77 GB | ✓ Yes | 32K | — |
| Q5_K_M | 67.1 GB | ✓ Yes | 64K | — |
| Q4_K_M | 57.8 GB | ✓ Yes | 64K | — |
| Q3_K_M | 42 GB | ✓ Yes | 64K | — |
| Q2_K | 33.3 GB | ✓ Yes | 64K | — |
Assumes an 8K-token context with an f16 KV cache. A longer window needs more; a quantized KV cache needs less. “Max context” is the largest window that still fits in 96 GB. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.
Context costs VRAM too. At Q4_K_M on the NVIDIA RTX PRO 6000 Blackwell: 8K 57.8 GB · 32K 67.8 GB · 125K 106.8 GB ✗. Past 125K it no longer fits 96 GB — a q8_0 KV cache buys roughly half of that back, which the calculator will price for you.
What to do next
Nothing to change — run it at Q4_K_M. If you want more capability, check whether the next size up also fits.
No compatible GPU? Llama 3.2 Vision on 8 GB of system RAM, CPU only: runs.
Running Llama 3.2 Vision 90B on this card:
At 2 hrs/day, buying (~$8,565) beats renting at $0.77/hr after about 15.4 years.
Affiliate links — we may earn a commission if you sign up, at no extra cost to you.
Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.
Other Llama 3.2 Vision sizes on the NVIDIA RTX PRO 6000 Blackwell
- Llama 3.2 Vision 11B — runs (8.5 GB)
Llama 3.2 Vision 90B on nearby hardware
- NVIDIA H100 80GB (PCIe) (80 GB) — runs
- Apple M4 Max (128 GB) — runs
All Llama 3.2 Vision sizes on the NVIDIA RTX PRO 6000 Blackwell | Llama 3.2 Vision 90B model page | NVIDIA RTX PRO 6000 Blackwell GPU page | VRAM calculator | Check your hardware