mv3 IQ3 XXS needs about 0.8 GB of memory at IQ3_XXS (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU.
mv3 IQ3 XXS is a 810M-parameter Xxs model in GGUF format, quantized by SixOpen. The repository has 1 quant file, from 0.3 GB (IQ3_XXS) to 0.3 GB (IQ3_XXS).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_XXS | 0.3 GB | 0.8 GB | Fits | Get file → |
What GPU do you need for mv3 IQ3 XXS?
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 IQ3_XXS (0.3 GB file, about 0.8 GB in use).
Which mv3 IQ3 XXS quant should you choose?
IQ3_XXS (0.3 GB) is the middle option in this repository. 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 mv3 IQ3 XXS
How much VRAM does mv3 IQ3 XXS need?
About 0.8 GB at IQ3_XXS 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 mv3 IQ3 XXS on an 8 GB GPU?
Yes, with IQ3_XXS: the 0.3 GB file needs about 0.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of mv3 IQ3 XXS GGUF?
It depends on the quant: IQ3_XXS is 0.3 GB.
Where can I download mv3 IQ3 XXS GGUF?
The files are on Hugging Face in the SixOpen/mv3-IQ3_XXS.gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.