maegic needs about 0.6 GB of memory at Q6_K (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.1 GB (Q6_K) to 2.9 GB (IQ4_XS).
maegic is a Maegic model in GGUF format, quantized by TobDeBer. The repository has 2 quant files, from 0.1 GB (Q6_K) to 2.9 GB (IQ4_XS).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K | 0.1 GB | 0.6 GB | Fits | Get file → | |
| IQ4_XS | 2.9 GB | 3.7 GB | Fits | Get file → |
What GPU do you need for maegic?
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 IQ4_XS (2.9 GB file, about 3.7 GB in use).
Which maegic quant should you choose?
Q6_K (0.1 GB) is the middle option in this repository. 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 maegic
How much VRAM does maegic need?
About 0.6 GB at Q6_K with an 8K context window. That is the 0.1 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 maegic on an 8 GB GPU?
Yes, with IQ4_XS: the 2.9 GB file needs about 3.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of maegic GGUF?
It depends on the quant: Q6_K is 0.1 GB, IQ4_XS is 2.9 GB.
Where can I download maegic GGUF?
The files are on Hugging Face in the TobDeBer/maegic repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does maegic 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.