Murasaki Backup needs about 9.8 GB of memory at IQ4_XS (a 8.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 5 quants, from 3.6 GB (Q6_K) to 29.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
Murasaki Backup – 14.8B Qwen3 model in multiple GGUF quantizations
Murasaki Backup is a 14.8B parameter Qwen3 model available in several GGUF quantizations. It supports up to 32768 context tokens and is released under the MIT license. The model is provided as a backup of deleted repositories.
Good at
- Large context handling
- Flexible quantization options
- MIT licensed
Limits
- No vision support
- Requires 8k context for memory estimates
- No mixture of experts
Best for
- Long-form text generation
- Context‑heavy dialogue
- Research prototyping
Who it’s for. Developers and researchers needing a large‑parameter Qwen3 model with flexible quantization. The model is suitable for local inference on systems with sufficient VRAM and RAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K | 3.6 GB | 5.3 GB | Fits | Get file → | |
| Q6_K | 6.7 GB | 8.4 GB | Too big | Get file → | |
| IQ4_XS | 8.1 GB | 9.8 GB | Too big | Get file → | |
| Q6_K | 12.1 GB | 13.8 GB | Too big | Get file → | |
| F16 | 29.5 GB | 31.3 GB | Too big | Get file → |
For 8‑GB VRAM, use the Q6_K 3.63‑GB file (≈5.3‑GB memory). For 12‑GB VRAM, the Q6_K 6.73‑GB file (≈8.4‑GB memory) is suitable. For larger budgets, the IQ4_XS 8.11‑GB or Q6_K 12.12‑GB files provide higher quality at increased memory usage.
What GPU do you need for Murasaki Backup?
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: the best quant that fits is Q6_K (3.6 GB file, about 5.3 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (3.6 GB file, about 5.3 GB in use).
- 12 GB VRAM: the best quant that fits is IQ4_XS (8.1 GB file, about 9.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (12.1 GB file, about 13.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (12.1 GB file, about 13.8 GB in use).
- 32 GB VRAM: the best quant that fits is F16 (29.5 GB file, about 31.3 GB in use).
Which Murasaki Backup quant should you choose?
IQ4_XS (8.1 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 Q6_K at 3.6 GB, with the quality trade-offs that come with fewer bits. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Murasaki Backup
How much VRAM does Murasaki Backup need?
About 9.8 GB at IQ4_XS with an 8K context window. That is the 8.1 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 Murasaki Backup on an 8 GB GPU?
Yes, with Q6_K: the 3.6 GB file needs about 5.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Murasaki Backup GGUF?
It depends on the quant: Q6_K is 3.6 GB, Q6_K is 6.7 GB, IQ4_XS is 8.1 GB, Q6_K is 12.1 GB, F16 is 29.5 GB.
What context length does Murasaki Backup support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.
Where can I download Murasaki Backup GGUF?
The files are on Hugging Face in the shoutmon/Murasaki-Backup repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Murasaki Backup 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.
Can I run Murasaki Backup on 8 GB VRAM?
Yes, the Q6_K 3.63‑GB quantization requires about 5.3‑GB memory at 8k context, fitting within 8‑GB VRAM.
Does the model support image inputs?
No, Murasaki Backup does not include vision capabilities.
What license applies to this model?
The model is released under the MIT license, allowing free use and modification.