Vinci MLE 30B 1.0 needs about 20.1 GB of memory at Q4_K_M (a 17.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 17.5 GB (Q4_K_M) to 57.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
Vinci MLE 30B 1.0 is a 28.9B-parameter Vinci model in GGUF format, quantized by simpledirect. Its trained context length is 128K tokens. The repository has 4 quant files, from 17.5 GB (Q4_K_M) to 57.7 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 17.5 GB | 20.1 GB | Too big | Get file → | |
| Q5_K_M | 20.5 GB | 23.1 GB | Too big | Get file → | |
| Q8_0 | 30.7 GB | 33.3 GB | Too big | Get file → | |
| F16 | 57.7 GB | 60.4 GB | Too big | Get file → |
What GPU do you need for Vinci MLE 30B 1.0?
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 Q5_K_M (20.5 GB file, about 23.1 GB in use).
- 32 GB VRAM: the best quant that fits is Q5_K_M (20.5 GB file, about 23.1 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (30.7 GB file, about 33.3 GB in use).
Which Vinci MLE 30B 1.0 quant should you choose?
Q4_K_M is the usual starting point for Vinci MLE 30B 1.0: it balances file size and quality well. Here it is a 17.5 GB file.
The Q8_0 file is 30.7 GB, about 1.8 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 Vinci MLE 30B 1.0
How much VRAM does Vinci MLE 30B 1.0 need?
About 20.1 GB at Q4_K_M with an 8K context window. That is the 17.5 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 Vinci MLE 30B 1.0 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 20.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Vinci MLE 30B 1.0 GGUF?
It depends on the quant: Q4_K_M is 17.5 GB, Q5_K_M is 20.5 GB, Q8_0 is 30.7 GB, F16 is 57.7 GB.
What context length does Vinci MLE 30B 1.0 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download Vinci MLE 30B 1.0 GGUF?
The files are on Hugging Face in the simpledirect/Vinci-MLE-30B-1.0-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 Vinci MLE 30B 1.0 use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.