DFM Mimir needs about 10.5 GB of memory at BF16 (a 3.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 1.9 GB (Q8_0) to 3.6 GB (F16).
DFM Mimir is a 1.79B-parameter Dfm model in GGUF format, quantized by noctrex. Its trained context length is 4K tokens. The repository has 3 quant files, from 1.9 GB (Q8_0) to 3.6 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 1.9 GB | 5.6 GB | Fits | Get file → | |
| BF16 | 3.6 GB | 7.3 GB | Tight | Get file → | |
| F16 | 3.6 GB | 7.3 GB | Tight | Get file → |
What GPU do you need for DFM Mimir?
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 BF16 (3.6 GB file, about 10.5 GB in use).
Which DFM Mimir quant should you choose?
BF16 (3.6 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
If memory is tight, the smallest file is Q8_0 at 1.9 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about DFM Mimir
How much VRAM does DFM Mimir need?
About 10.5 GB at BF16 with an 8K context window. That is the 3.6 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 DFM Mimir on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of DFM Mimir GGUF?
It depends on the quant: Q8_0 is 1.9 GB, BF16 is 3.6 GB, F16 is 3.6 GB.
What context length does DFM Mimir support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.4 GB at 8K and 3.2 GB at 4K.
Where can I download DFM Mimir GGUF?
The files are on Hugging Face in the noctrex/DFM-Mimir repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does DFM Mimir 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.