72B preview needs about 65.7 GB of memory at Q4_K_M (a 43.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 30.4 GB (Q2_K) to 43.8 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 85.9 GB.
72B preview is a 72.3B-parameter Preview model in GGUF format, quantized by CausalLM. Its trained context length is 32K tokens. The repository has 3 quant files, from 30.4 GB (Q2_K) to 43.8 GB (Q4_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 30.4 GB | 52.3 GB | Too big | Get file → | |
| Q3_K_M | 35.2 GB | 57.2 GB | Too big | Get file → | |
| Q4_K_M | 43.8 GB | 65.7 GB | Too big | Get file → |
What GPU do you need for 72B preview?
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 72B preview quant should you choose?
Q4_K_M is the usual starting point for 72B preview: it balances file size and quality well. Here it is a 43.8 GB file.
If memory is tight, the smallest file is Q2_K at 30.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about 72B preview
How much VRAM does 72B preview need?
About 65.7 GB at Q4_K_M with an 8K context window. That is the 43.8 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 72B preview on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 52.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of 72B preview GGUF?
It depends on the quant: Q2_K is 30.4 GB, Q3_K_M is 35.2 GB, Q4_K_M is 43.8 GB.
What context length does 72B preview support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 21.5 GB at 8K and 85.9 GB at 32K.
Where can I download 72B preview GGUF?
The files are on Hugging Face in the CausalLM/72B-preview-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does 72B preview use?
Hugging Face lists the license as gpl-3.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.