Mira Demeter needs about 21.2 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 10.5 GB (Q2_K) to 28.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 16.6 GB.
Mira Demeter is a 27B-parameter Mira model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 11 quant files, from 10.5 GB (Q2_K) to 28.7 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 10.5 GB | 15.2 GB | Too big | Get file → | |
| Q3_K_S | 12.2 GB | 16.8 GB | Too big | Get file → | |
| Q3_K_M | 13.4 GB | 18.1 GB | Too big | Get file → | |
| Q3_K_L | 14.5 GB | 19.2 GB | Too big | Get file → | |
| IQ4_XS | 14.9 GB | 19.6 GB | Too big | Get file → | |
| Q4_K_S | 15.7 GB | 20.3 GB | Too big | Get file → | |
| Q4_K_M | 16.5 GB | 21.2 GB | Too big | Get file → | |
| Q5_K_S | 18.8 GB | 23.4 GB | Too big | Get file → | |
| Q5_K_M | 19.3 GB | 23.9 GB | Too big | Get file → | |
| Q6_K | 22.2 GB | 26.8 GB | Too big | Get file → | |
| Q8_0 | 28.7 GB | 33.4 GB | Too big | Get file → |
What GPU do you need for Mira Demeter?
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: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is Q2_K (10.5 GB file, about 15.2 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (19.3 GB file, about 23.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (22.2 GB file, about 26.8 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (28.7 GB file, about 33.4 GB in use).
Which Mira Demeter quant should you choose?
Q4_K_M is the usual starting point for Mira Demeter: it balances file size and quality well. Here it is a 16.5 GB file.
The Q8_0 file is 28.7 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 10.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Mira Demeter
How much VRAM does Mira Demeter need?
About 21.2 GB at Q4_K_M with an 8K context window. That is the 16.5 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 Mira Demeter on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 15.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Mira Demeter GGUF?
It depends on the quant: Q2_K is 10.5 GB, Q3_K_S is 12.2 GB, Q3_K_M is 13.4 GB, Q3_K_L is 14.5 GB, IQ4_XS is 14.9 GB, Q4_K_S is 15.7 GB and 5 more.
What context length does Mira Demeter support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.2 GB at 8K and 16.6 GB at 32K.
Where can I download Mira Demeter GGUF?
The files are on Hugging Face in the mradermacher/Mira-Demeter-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.