Llama 3.2 90B Vision Instruct — VRAM, speed & local setup
Written by Jakub Rusinowski · Last updated
The flagship open vision model. Near GPT-4V quality for image understanding. Requires 48GB+ VRAM or multi-GPU setup. Listed in full on the dedicated Llama 3.2 Vision page, which is the canonical entry for this model and carries the install command.
Llama 3.2 90B Vision Instruct needs about 54 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
VRAM and speed by quantization
Quoted against NVIDIA RTX 4090 (24 GB). Includes the KV cache at 8K context, so it reads higher than the headline figure.
| Quant | Memory | VRAM | Speed (est.) | Fit |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 33.3 GB | ~3 tok/s | Offload | |
| Q3_K_M 3.41 bpw | 42 GB | ~3 tok/s | Offload | |
| Q4_K_M 4.83 bpw | 57.8 GB | — | Too big | |
| Q5_K_M 5.67 bpw | 67.1 GB | — | Too big | |
| Q6_K 6.56 bpw | 77 GB | — | Too big | |
| Q8_0 8.50 bpw | 98.5 GB | — | Too big | |
| F16 16.00 bpw | 181.8 GB | — | Too big |
Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. Llama 3.2 90B Vision Instruct VRAM calculator →
Get Llama 3.2 90B Vision Instruct running
The cheapest catalogued GPU that runs Llama 3.2 90B Vision Instruct is the NVIDIA DGX Spark (128 GB).
or compare on Vast.ai from $0.77/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
How to run Llama 3.2 90B Vision Instruct
Install Ollama, then run:
ollama run llama-3-2Specifications
Curated — A hand-written entry from before this catalogue recorded its sources. The figures are long-standing but their provenance is not on file.
- Parameters
- 90 Billion
- Context window
- 128,000
- Architecture
- Dense + Vision Encoder
- Provider
- Meta
- Licence
- Llama Community
- Practical deployment
- Workstation (large unified memory or pro GPU)
- Specified at
- Q4_K_M
- System RAM
- 128 GB
- Record updated
- 2026-08-15
Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.
Quality and use cases
Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.
Can I run Llama 3.2 90B Vision Instruct on my GPU?
- Llama 3.2 90B Vision Instruct on AMD Radeon RX 9060 XT 8GB
- Llama 3.2 90B Vision Instruct on AMD Ryzen AI Max+ 395
- Llama 3.2 90B Vision Instruct on Apple M1 Ultra
- Llama 3.2 90B Vision Instruct on Apple M2 Max
- Llama 3.2 90B Vision Instruct on Apple M4 Max
- Llama 3.2 90B Vision Instruct on Apple M5 Max
- Llama 3.2 90B Vision Instruct on Intel Arc B570
- Llama 3.2 90B Vision Instruct on Intel Arc B580
- Llama 3.2 90B Vision Instruct on NVIDIA A100 80GB (PCIe)
- Llama 3.2 90B Vision Instruct on NVIDIA DGX Spark
- Llama 3.2 90B Vision Instruct on NVIDIA GeForce RTX 3060 (12GB)
- Llama 3.2 90B Vision Instruct on NVIDIA GeForce RTX 3070
- Llama 3.2 90B Vision Instruct on NVIDIA GeForce RTX 3070 Ti
- Llama 3.2 90B Vision Instruct on NVIDIA GeForce RTX 3080 (10GB)
- Llama 3.2 90B Vision Instruct on NVIDIA GeForce RTX 4060
- Llama 3.2 90B Vision Instruct on NVIDIA GeForce RTX 4070
- Llama 3.2 90B Vision Instruct on NVIDIA GeForce RTX 4070 Super
- Llama 3.2 90B Vision Instruct on NVIDIA GeForce RTX 4070 Ti
- Llama 3.2 90B Vision Instruct on NVIDIA GeForce RTX 5060
- Llama 3.2 90B Vision Instruct on NVIDIA GeForce RTX 5060 Ti 8GB
- Llama 3.2 90B Vision Instruct on NVIDIA GeForce RTX 5070
- Llama 3.2 90B Vision Instruct on NVIDIA H100 80GB (PCIe)
- Llama 3.2 90B Vision Instruct on NVIDIA RTX PRO 6000 Blackwell
Other Llama 3.2 Family sizes
Llama 3.2 90B Vision Instruct — frequently asked questions
How much VRAM does Llama 3.2 90B Vision Instruct need?
About 54 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does Llama 3.2 90B Vision Instruct run on an RTX 4090 (24 GB)?
No. Llama 3.2 90B Vision Instruct needs about 54 GB at Q4_K_M, more than a single RTX 4090's 24 GB. It needs a larger card, several GPUs, or Apple Silicon with enough unified memory — or it runs with part of the weights offloaded to system RAM, which is much slower.
How do I run Llama 3.2 90B Vision Instruct locally?
Install Ollama and run `ollama run llama-3-2`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does Llama 3.2 Family come in?
Llama 3.2 1B Instruct (2 GB), Llama 3.2 3B Instruct (3 GB), Llama 3.2 11B Vision Instruct (7 GB), Llama 3.2 90B Vision Instruct (54 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.