Mirror 80M MoE needs about 0.9 GB of memory at Q8_0 (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 7 quants, from 0.3 GB to 0.3 GB (Q8_0).
Mirror 80M MoE is a 81M-parameter Mirror model in GGUF format, quantized by dipeshmajithia. Its trained context length is 512 tokens. The repository has 7 quant files, from 0.3 GB to 0.3 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.3 GB | 0.8 GB | Fits | Get file → | |
| F32 | 0.3 GB | 0.8 GB | Fits | Get file → | |
| Q4_K | 0.3 GB | 0.8 GB | Fits | Get file → | |
| Q8_0 | 0.3 GB | 0.8 GB | Fits | Get file → | |
| F32 | 0.3 GB | 0.8 GB | Fits | Get file → | |
| Q4_K | 0.3 GB | 0.8 GB | Fits | Get file → | |
| Q8_0 | 0.3 GB | 0.8 GB | Fits | Get file → |
What GPU do you need for Mirror 80M MoE?
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 F32 (0.3 GB file, about 0.9 GB in use).
Which Mirror 80M MoE quant should you choose?
Q8_0 (0.3 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
If memory is tight, the smallest file is the first one in the table at 0.3 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Mirror 80M MoE
How much VRAM does Mirror 80M MoE need?
About 0.9 GB at Q8_0 with an 8K context window. That is the 0.3 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 Mirror 80M MoE on an 8 GB GPU?
Yes, with F32: the 0.3 GB file needs about 0.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Mirror 80M MoE GGUF?
It depends on the quant: file is 0.3 GB, F32 is 0.3 GB, Q4_K is 0.3 GB, Q8_0 is 0.3 GB, F32 is 0.3 GB, Q4_K is 0.3 GB and 1 more.
What context length does Mirror 80M MoE support?
The GGUF header lists a trained context length of 512 tokens (512).
Where can I download Mirror 80M MoE GGUF?
The files are on Hugging Face in the dipeshmajithia/Mirror-80M-MoE-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 Mirror 80M MoE use?
Hugging Face lists the license as cc-by-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.