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 21 quants, from 9.8 GB (IQ1_S) to 38.4 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
DonutHole-8x7B – a 46.7B parameter llama-based model with 32k context
DonutHole-8x7B is a 46.7B parameter llama architecture model merged from multiple sources. It supports 32768 context tokens and is licensed under apache-2.0. The model is available in a variety of GGUF quantizations.
Good at
- Alpaca prompt formats
- Mistral format
- Long‑context generation up to 32k tokens
Limits
- No vision support
- Requires large VRAM for higher quant levels
- No explicit language support listed
Best for
- Instruction following in text‑only environments
- Fine‑tuning with custom prompts
- Research on large‑context language models
Who it’s for. Developers and researchers who need a large llama‑based model with extended context. The model is suitable for use in llama.cpp or other GGUF‑compatible runtimes.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 9.8 GB | 11.4 GB | Too big | Get file → | |
| IQ1_M | 10.8 GB | 12.4 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 → | |
| Q2_K | 17.3 GB | 18.9 GB | Too big | Get file → | |
| IQ3_XXS | 18.2 GB | 19.8 GB | Too big | Get file → | |
| IQ3_XS | 19.4 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_XS | 25.1 GB | 26.7 GB | Too big | Get file → | |
| Q4_0 | 26.6 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 → | |
| Q6_K | 38.4 GB | 40.0 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (9.82 GB) or IQ1_M (10.85 GB). For 16 GB VRAM, IQ2_M (15.5 GB) or Q2_K (17.31 GB) are suitable. For 24 GB VRAM, Q4_K_M (28.45 GB) or Q5_K_S (32.23 GB) provide higher quality. 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.
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, IQ1_M is 10.8 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 and 15 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 mradermacher/DonutHole-8x7B-i1-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 IQ1_S or IQ1_M quantizations. They are 9.82 GB and 10.85 GB respectively, which fit within 8 GB VRAM when accounting for overhead.
Does DonutHole-8x7B support vision tasks?
No, the model has no vision capabilities.