Macaron V1 Coding Venti needs about 213.2 GB of memory at its main file (a 211.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 211.3 GB to 211.3 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.
Macaron V1 Coding Venti is a 753B-parameter Macaron model in GGUF format, quantized by sokann. Its trained context length is 1024K tokens. The repository has 2 quant files, from 211.3 GB to 211.3 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 211.3 GB | 213.2 GB | Too big | Get file → | |
| — | 211.3 GB | 213.2 GB | Too big | Get file → |
What GPU do you need for Macaron V1 Coding Venti?
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.
Specifications
Architecture from the GGUF header
Frequently asked questions about Macaron V1 Coding Venti
How much VRAM does Macaron V1 Coding Venti need?
About 213.2 GB at its main file with an 8K context window. That is the 211.3 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 Macaron V1 Coding Venti on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 213.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Macaron V1 Coding Venti GGUF?
It depends on the quant: file is 211.3 GB, file is 211.3 GB.
What context length does Macaron V1 Coding Venti support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.
Where can I download Macaron V1 Coding Venti GGUF?
The files are on Hugging Face in the sokann/Macaron-V1-Coding-Venti-GGUF-2.244bpw repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Macaron V1 Coding Venti use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.