Holo 3.1 35B A3B MTP needs about 20.9 GB of memory at IQ4_XS (a 18.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 10 quants, from 0.2 GB to 30.0 GB (Q6_K).
Holo 3.1 35B A3B MTP is a 447M-parameter Holo model in GGUF format, quantized by gbuzhf. The repository has 10 quant files, from 0.2 GB to 30.0 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.2 GB | 0.7 GB | Fits | Get file → | |
| — | 14.3 GB | 16.5 GB | Too big | Get file → | |
| — | 17.3 GB | 19.9 GB | Too big | Get file → | |
| — | 17.3 GB | 19.9 GB | Too big | Get file → | |
| IQ4_XS | 18.2 GB | 20.9 GB | Too big | Get file → | |
| Q4_K_XL | 22.9 GB | 26.1 GB | Too big | Get file → | |
| — | 23.5 GB | 26.8 GB | Too big | Get file → | |
| Q5_K_S | 25.5 GB | 29.1 GB | Too big | Get file → | |
| — | 26.1 GB | 29.7 GB | Too big | Get file → | |
| Q6_K | 30.0 GB | 34.1 GB | Too big | Get file → |
What GPU do you need for Holo 3.1 35B A3B MTP?
These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is the main file (0.2 GB file, about 0.7 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 0.7 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 0.7 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 0.7 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 0.7 GB in use).
- 24 GB VRAM: the best quant that fits is IQ4_XS (18.2 GB file, about 20.9 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (26.1 GB file, about 29.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (30.0 GB file, about 34.1 GB in use).
Which Holo 3.1 35B A3B MTP quant should you choose?
IQ4_XS (18.2 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is the first one in the table at 0.2 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Holo 3.1 35B A3B MTP
How much VRAM does Holo 3.1 35B A3B MTP need?
About 20.9 GB at IQ4_XS with an 8K context window. That is the 18.2 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 Holo 3.1 35B A3B MTP on an 8 GB GPU?
Yes, with the smaller files: the 0.2 GB file needs about 0.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Holo 3.1 35B A3B MTP GGUF?
It depends on the quant: file is 0.2 GB, file is 14.3 GB, file is 17.3 GB, file is 17.3 GB, IQ4_XS is 18.2 GB, Q4_K_XL is 22.9 GB and 4 more.
Where can I download Holo 3.1 35B A3B MTP GGUF?
The files are on Hugging Face in the gbuzhf/Holo-3.1-35B-A3B-MTP-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 Holo 3.1 35B A3B MTP 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.