Can I Run Llama 3.2 90B Vision Instruct on NVIDIA GeForce RTX 4070 Super?
作者： Jakub Rusinowski · 最后更新： 2026年9月19日
No. Llama 3.2 90B Vision Instruct needs 53.6 GB at Q4_K_M and the NVIDIA GeForce RTX 4070 Super has only 12 GB. No quantization we publish closes a gap that size.
Get a personalized upgrade path →
The numbers
| Model | Llama 3.2 90B Vision Instruct |
| Parameters | 90B |
| Quantization | Q4_K_M |
| VRAM needed | 53.6 GB |
| NVIDIA GeForce RTX 4070 Super VRAM | 12 GB |
| Verdict | Does not fit |
Llama 3.2 90B Vision Instruct on the NVIDIA GeForce RTX 4070 Super: VRAM by quantization
| Quant | VRAM needed | Fits 12 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 180.1 GB | ✗ No | — | — |
| Q8_0 | 96.8 GB | ✗ No | — | — |
| Q6_K | 75.3 GB | ✗ No | — | — |
| Q5_K_M | 65.4 GB | ✗ No | — | — |
| Q4_K_M | 56.1 GB | ✗ No | — | — |
| Q3_K_M | 40.3 GB | ✗ No | — | — |
| Q2_K | 31.7 GB | ✗ No | — | — |
Assumes a 4K-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 12 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 GeForce RTX 4070 Super: 8K 57.8 GB ✗ · 32K 67.8 GB ✗ · 125K 106.8 GB ✗. Past 8K it no longer fits 12 GB — a q8_0 KV cache buys roughly half of that back, which the calculator will price for you.
What to do next
Either step down to a smaller size in this family, or move to a Apple M1 Max (64 GB), the cheapest card we track with enough VRAM.
No compatible GPU? Llama 3.2 Family on 8 GB of system RAM, CPU only: runs.
Cheapest card we track with enough VRAM for Llama 3.2 90B Vision Instruct:
Llama 3.2 90B Vision Instruct needs ~54 GB but this GPU has 12 GB. Rent a A100 (80 GB)-class GPU by the hour instead of buying one:
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 Family sizes on the NVIDIA GeForce RTX 4070 Super
- Llama 3.2 11B Vision Instruct — runs (6.4 GB)
- Llama 3.2 3B Instruct — runs (1.9 GB)
- Llama 3.2 1B Instruct — runs (0.7 GB)
Llama 3.2 90B Vision Instruct on nearby hardware
- Intel Arc B570 (10 GB) — does not fit
- NVIDIA A100 80GB (PCIe) (80 GB) — runs
All Llama 3.2 Family sizes on the NVIDIA GeForce RTX 4070 Super | Llama 3.2 90B Vision Instruct model page | NVIDIA GeForce RTX 4070 Super GPU page | Check your hardware