Dracarys 72B Instruct needs about 50.6 GB of memory at Q4_K_M (a 47.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 18 quants, from 17.9 GB (Q8_0) to 64.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
Dracarys 72B Instruct is a 72.7B-parameter Dracarys model in GGUF format, quantized by RichardErkhov. Its trained context length is 32K tokens. The repository has 18 quant files, from 17.9 GB (Q8_0) to 64.3 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 17.9 GB | 21.0 GB | Too big | Get file → | |
| Q2_K | 29.8 GB | 33.0 GB | Too big | Get file → | |
| Q3_K_S | 34.5 GB | 37.7 GB | Too big | Get file → | |
| Q3_K | 37.7 GB | 40.9 GB | Too big | Get file → | |
| Q3_K_M | 37.7 GB | 40.9 GB | Too big | Get file → | |
| Q3_K_L | 39.5 GB | 42.7 GB | Too big | Get file → | |
| IQ4_XS | 40.2 GB (2 parts) | 43.3 GB | Too big | Get file → | |
| Q4_0 | 41.2 GB (2 parts) | 44.4 GB | Too big | Get file → | |
| IQ4_NL | 41.8 GB (2 parts) | 45.0 GB | Too big | Get file → | |
| Q4_K_S | 43.9 GB (2 parts) | 47.1 GB | Too big | Get file → | |
| Q4_1 | 45.7 GB (2 parts) | 48.9 GB | Too big | Get file → | |
| Q4_K | 47.4 GB (2 parts) | 50.6 GB | Too big | Get file → | |
| Q4_K_M | 47.4 GB (2 parts) | 50.6 GB | Too big | Get file → | |
| Q5_0 | 50.2 GB (2 parts) | 53.3 GB | Too big | Get file → | |
| Q5_K_S | 51.4 GB (2 parts) | 54.6 GB | Too big | Get file → | |
| Q5_K | 54.4 GB (2 parts) | 57.6 GB | Too big | Get file → | |
| Q5_1 | 54.6 GB (2 parts) | 57.8 GB | Too big | Get file → | |
| Q6_K | 64.3 GB (2 parts) | 67.5 GB | Too big | Get file → |
What GPU do you need for Dracarys 72B 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: the best quant that fits is Q8_0 (17.9 GB file, about 21.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (17.9 GB file, about 21.0 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_K_S (43.9 GB file, about 47.1 GB in use).
Which Dracarys 72B Instruct quant should you choose?
Q4_K_M is the usual starting point for Dracarys 72B Instruct: it balances file size and quality well. Here it is a 47.4 GB file.
The Q8_0 file is 17.9 GB, about 0.4 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.
If memory is tight, the smallest file is Q8_0 at 17.9 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Dracarys 72B Instruct
How much VRAM does Dracarys 72B Instruct need?
About 50.6 GB at Q4_K_M with an 8K context window. That is the 47.4 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 Dracarys 72B Instruct on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 21.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Dracarys 72B Instruct GGUF?
It depends on the quant: Q8_0 is 17.9 GB, Q2_K is 29.8 GB, Q3_K_S is 34.5 GB, Q3_K is 37.7 GB, Q3_K_M is 37.7 GB, Q3_K_L is 39.5 GB and 12 more.
What context length does Dracarys 72B Instruct support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.
Where can I download Dracarys 72B Instruct GGUF?
The files are on Hugging Face in the RichardErkhov/abacusai_-_Dracarys-72B-Instruct-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 Dracarys 72B Instruct use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.