DonutHole 8x7B needs about 30.0 GB of memory at Q4_K_M (a 28.4 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 20 quants, from 9.8 GB (IQ1_S) to 49.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
DonutHole 8x7B – a 46.7B parameter Mistral‑based model in GGUF format
DonutHole 8x7B is a 46.7B parameter Mistral‑style model quantized into GGUF files. It supports Alpaca and Mistral prompt formats and was trained with a 32768 token context window. The model is released under the Apache‑2.0 license.
Good at
- Alpaca instruction format
- Mistral prompt format
- Large context handling
Limits
- No vision support
- Requires 8k context for memory estimates
- License is Apache‑2.0
Best for
- Chatbot development
- Role‑playing scripts
- Instruction‑based generation
Who it’s for. Developers building chat or instruction‑based applications who need a large context model. The model is suitable for users comfortable with GGUF and llama.cpp quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 9.8 GB | 11.4 GB | Too big | Get file → | |
| IQ2_XXS | 12.6 GB | 14.1 GB | Too big | Get file → | |
| IQ2_XS | 13.9 GB | 15.5 GB | Too big | Get file → | |
| IQ2_S | 14.1 GB | 15.7 GB | Too big | Get file → | |
| IQ2_M | 15.5 GB | 17.1 GB | Too big | Get file → | |
| IQ3_XXS | 18.2 GB | 19.8 GB | Too big | Get file → | |
| IQ3_XS | 19.3 GB | 20.9 GB | Too big | Get file → | |
| IQ3_S | 20.4 GB | 22.0 GB | Too big | Get file → | |
| Q3_K_S | 20.4 GB | 22.0 GB | Too big | Get file → | |
| IQ3_M | 21.4 GB | 23.0 GB | Too big | Get file → | |
| Q3_K_M | 22.5 GB | 24.1 GB | Too big | Get file → | |
| Q3_K_L | 24.2 GB | 25.7 GB | Too big | Get file → | |
| IQ4_NL | 26.5 GB | 28.1 GB | Too big | Get file → | |
| Q4_K_S | 26.7 GB | 28.3 GB | Too big | Get file → | |
| Q4_K_M | 28.4 GB | 30.0 GB | Too big | Get file → | |
| Q5_K_S | 32.2 GB | 33.8 GB | Too big | Get file → | |
| Q5_K_M | 33.2 GB | 34.8 GB | Too big | Get file → | |
| Q5_1 | 35.1 GB | 36.7 GB | Too big | Get file → | |
| Q6_K | 38.4 GB | 40.0 GB | Too big | Get file → | |
| Q8_0 | 49.6 GB | 51.2 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_XXS (12.55 GB file, 14.1 GB memory at 8k). For 16 GB VRAM, IQ4_K_M (28.44 GB file, 30 GB memory) or Q5_K_S (32.23 GB file, 33.8 GB memory). For 32 GB VRAM, Q6_K (38.38 GB file, 40 GB memory) or Q8_0 (49.62 GB file, 51.2 GB memory). Estimates are approximate.
What GPU do you need for DonutHole 8x7B?
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: the best quant that fits is IQ1_S (9.8 GB file, about 11.4 GB in use).
- 16 GB VRAM: the best quant that fits is IQ2_S (14.1 GB file, about 15.7 GB in use).
- 24 GB VRAM: the best quant that fits is IQ3_M (21.4 GB file, about 23.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K_M (28.4 GB file, about 30.0 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (38.4 GB file, about 40.0 GB in use).
Which DonutHole 8x7B quant should you choose?
Q4_K_M is the usual starting point for DonutHole 8x7B: it balances file size and quality well. Here it is a 28.4 GB file.
The Q8_0 file is 49.6 GB, about 1.7 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 IQ1_S at 9.8 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about DonutHole 8x7B
How much VRAM does DonutHole 8x7B need?
About 30.0 GB at Q4_K_M with an 8K context window. That is the 28.4 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 DonutHole 8x7B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of DonutHole 8x7B GGUF?
It depends on the quant: IQ1_S is 9.8 GB, IQ2_XXS is 12.6 GB, IQ2_XS is 13.9 GB, IQ2_S is 14.1 GB, IQ2_M is 15.5 GB, IQ3_XXS is 18.2 GB and 14 more.
What context length does DonutHole 8x7B support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download DonutHole 8x7B GGUF?
The files are on Hugging Face in the ycros/DonutHole-8x7B-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 DonutHole 8x7B 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.
Can I run DonutHole 8x7B on 8 GB VRAM?
Use the IQ2_XXS quantized file, which is 12.55 GB and requires about 14.1 GB of VRAM at 8k context.
Does DonutHole 8x7B support vision tasks?
No, the model has no vision capabilities.
What license applies to DonutHole 8x7B?
The model is released under the Apache‑2.0 license.