Llama 3 pruned 45B Drobeta Turnu Severin needs about 29.3 GB of memory at Q4_K_M (a 27.1 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 6 quants, from 21.9 GB (Q3_K_M) to 89.8 GB.
Llama 3 pruned 45B Drobeta Turnu Severin is a 44.9B-parameter Llama model in GGUF format, quantized by AlenBadel. Its trained context length is 8K tokens. The repository has 6 quant files, from 21.9 GB (Q3_K_M) to 89.8 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 21.9 GB | 24.0 GB | Too big | Get file → | |
| Q4_K_S | 25.7 GB | 27.9 GB | Too big | Get file → | |
| Q4_K_M | 27.1 GB | 29.3 GB | Too big | Get file → | |
| Q5_K_S | 31.0 GB | 33.2 GB | Too big | Get file → | |
| Q5_K_M | 31.8 GB | 34.0 GB | Too big | Get file → | |
| — | 89.8 GB (3 parts) | 92.0 GB | Too big | Get file → |
What GPU do you need for Llama 3 pruned 45B Drobeta Turnu Severin?
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 Q3_K_M (21.9 GB file, about 24.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K_M (27.1 GB file, about 29.3 GB in use).
- 48 GB VRAM: the best quant that fits is Q5_K_M (31.8 GB file, about 34.0 GB in use).
Which Llama 3 pruned 45B Drobeta Turnu Severin quant should you choose?
Q4_K_M is the usual starting point for Llama 3 pruned 45B Drobeta Turnu Severin: it balances file size and quality well. Here it is a 27.1 GB file.
If memory is tight, the smallest file is Q3_K_M at 21.9 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Llama 3 pruned 45B Drobeta Turnu Severin
How much VRAM does Llama 3 pruned 45B Drobeta Turnu Severin need?
About 29.3 GB at Q4_K_M with an 8K context window. That is the 27.1 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 pruned 45B Drobeta Turnu Severin on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 24.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Llama 3 pruned 45B Drobeta Turnu Severin GGUF?
It depends on the quant: Q3_K_M is 21.9 GB, Q4_K_S is 25.7 GB, Q4_K_M is 27.1 GB, Q5_K_S is 31.0 GB, Q5_K_M is 31.8 GB, file is 89.8 GB.
What context length does Llama 3 pruned 45B Drobeta Turnu Severin support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.7 GB at 8K and 1.7 GB at 8K.
Where can I download Llama 3 pruned 45B Drobeta Turnu Severin GGUF?
The files are on Hugging Face in the AlenBadel/Llama-3-pruned-45B-Drobeta-Turnu-Severin-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 Llama 3 pruned 45B Drobeta Turnu Severin 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.