Llama 3.2 90B Vision Instruct needs about 59.4 GB of memory at Q4_K_M (a 55.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 55.6 GB (Q4_K_M) to 177.3 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 13.4 GB.
Llama 3.2 90B Vision Instruct is a 88.6B-parameter Llama model in GGUF format, quantized by GeorgyGUF. Its trained context length is 128K tokens. The repository has 3 quant files, from 55.6 GB (Q4_K_M) to 177.3 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 55.6 GB (2 parts) | 59.4 GB | Too big | Get file → | |
| Q8_0 | 95.8 GB (2 parts) | 99.6 GB | Too big | Get file → | |
| F16 | 177.3 GB (4 parts) | 181.2 GB | Too big | Get file → |
What GPU do you need for Llama 3.2 90B Vision Instruct?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which Llama 3.2 90B Vision Instruct quant should you choose?
Q4_K_M is the usual starting point for Llama 3.2 90B Vision Instruct: it balances file size and quality well. Here it is a 55.6 GB file.
The Q8_0 file is 95.8 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Llama 3.2 90B Vision Instruct
How much VRAM does Llama 3.2 90B Vision Instruct need?
About 59.4 GB at Q4_K_M with an 8K context window. That is the 55.6 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Llama 3.2 90B Vision Instruct on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 59.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Llama 3.2 90B Vision Instruct GGUF?
It depends on the quant: Q4_K_M is 55.6 GB, Q8_0 is 95.8 GB, F16 is 177.3 GB.
What context length does Llama 3.2 90B Vision Instruct support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.4 GB at 8K and 13.4 GB at 32K.
Where can I download Llama 3.2 90B Vision Instruct GGUF?
The files are on Hugging Face in the GeorgyGUF/Llama-3.2-90B-Vision-Instruct repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.