Magic 8B needs about 8.8 GB of memory at Q6_K (a 6.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 5 quants, from 5.9 GB (Q5_K_S) to 16.8 GB.
Magic 8B is a 8.41B-parameter Magic model in GGUF format, quantized by MaziyarPanahi. Its trained context length is 8K tokens. The repository has 5 quant files, from 5.9 GB (Q5_K_S) to 16.8 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K_S | 5.9 GB | 7.7 GB | Tight | Get file → | |
| Q5_K_M | 6.0 GB | 7.8 GB | Tight | Get file → | |
| Q6_K | 6.9 GB | 8.8 GB | Too big | Get file → | |
| Q8_0 | 8.9 GB | 10.8 GB | Too big | Get file → | |
| — | 16.8 GB | 18.7 GB | Too big | Get file → |
What GPU do you need for Magic 8B?
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: the best quant that fits is Q5_K_M (6.0 GB file, about 7.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.9 GB file, about 10.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.9 GB file, about 10.8 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (16.8 GB file, about 18.7 GB in use).
Which Magic 8B quant should you choose?
Q6_K (6.9 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.
If memory is tight, the smallest file is Q5_K_S at 5.9 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Magic 8B
How much VRAM does Magic 8B need?
About 8.8 GB at Q6_K with an 8K context window. That is the 6.9 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 Magic 8B on an 8 GB GPU?
Yes, with Q5_K_M: the 6.0 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Magic 8B GGUF?
It depends on the quant: Q5_K_S is 5.9 GB, Q5_K_M is 6.0 GB, Q6_K is 6.9 GB, Q8_0 is 8.9 GB, file is 16.8 GB.
What context length does Magic 8B support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.3 GB at 8K and 1.3 GB at 8K.
Where can I download Magic 8B GGUF?
The files are on Hugging Face in the MaziyarPanahi/Magic_8B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.