Raw_Mia v1 E6B needs about 20.8 GB of memory at Q4_K_M (a 7.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 6.1 GB (Q3_K_M) to 23.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 51.5 GB.
Raw_Mia v1 E6B is a 11.9B-parameter Raw model in GGUF format, quantized by veld-ai. Its trained context length is 256K tokens. The repository has 5 quant files, from 6.1 GB (Q3_K_M) to 23.8 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 6.1 GB | 19.5 GB | Too big | Get file → | |
| Q4_K_M | 7.4 GB | 20.8 GB | Too big | Get file → | |
| Q5_K_M | 8.5 GB | 21.9 GB | Too big | Get file → | |
| Q8_0 | 12.7 GB | 26.1 GB | Too big | Get file → | |
| F16 | 23.8 GB | 37.2 GB | Too big | Get file → |
What GPU do you need for Raw_Mia v1 E6B?
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: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q5_K_M (8.5 GB file, about 21.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (12.7 GB file, about 26.1 GB in use).
- 48 GB VRAM: the best quant that fits is F16 (23.8 GB file, about 37.2 GB in use).
Which Raw_Mia v1 E6B quant should you choose?
Q4_K_M is the usual starting point for Raw_Mia v1 E6B: it balances file size and quality well. Here it is a 7.4 GB file.
The Q8_0 file is 12.7 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 Q3_K_M at 6.1 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Raw_Mia v1 E6B
How much VRAM does Raw_Mia v1 E6B need?
About 20.8 GB at Q4_K_M with an 8K context window. That is the 7.4 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 Raw_Mia v1 E6B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 19.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Raw_Mia v1 E6B GGUF?
It depends on the quant: Q3_K_M is 6.1 GB, Q4_K_M is 7.4 GB, Q5_K_M is 8.5 GB, Q8_0 is 12.7 GB, F16 is 23.8 GB.
What context length does Raw_Mia v1 E6B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 12.9 GB at 8K and 51.5 GB at 32K.
Where can I download Raw_Mia v1 E6B GGUF?
The files are on Hugging Face in the veld-ai/Mia-v1-E6B-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 Raw_Mia v1 E6B 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.