Can I Run Llama 3.2 90B Vision Instruct on NVIDIA GeForce RTX 4070?

Autor: Jakub Rusinowski · Ostatnia aktualizacja: 11 września 2026

No. Llama 3.2 90B Vision Instruct needs 53.6 GB at Q4_K_M and the NVIDIA GeForce RTX 4070 has only 12 GB. No quantization we publish closes a gap that size.

Get a personalized upgrade path →

The numbers

Llama 3.2 90B Vision Instruct on the NVIDIA GeForce RTX 4070: VRAM by quantization

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: 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:

Other Llama 3.2 Family sizes on the NVIDIA GeForce RTX 4070

• 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 (80 GB) — runs

All Llama 3.2 Family sizes on the NVIDIA GeForce RTX 4070 | Llama 3.2 90B Vision Instruct model page | NVIDIA GeForce RTX 4070 GPU page | Check your hardware