Vezstral 3B Bolognese v3 needs about 3.5 GB of memory at its main file (a 2.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 3.5 GB.
Vezstral 3B Bolognese v3 is a 3.43B-parameter Mistral model in GGUF format, quantized by n1kg0r. Its trained context length is 256K tokens. The repository has 1 quant file, from 2.1 GB to 2.1 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 2.1 GB | 3.5 GB | Fits | Get file → |
What GPU do you need for Vezstral 3B Bolognese v3?
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: the best quant that fits is the main file (2.1 GB file, about 3.5 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Vezstral 3B Bolognese v3
How much VRAM does Vezstral 3B Bolognese v3 need?
About 3.5 GB at its main file with an 8K context window. That is the 2.1 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 Vezstral 3B Bolognese v3 on an 8 GB GPU?
Yes, with the smaller files: the 2.1 GB file needs about 3.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Vezstral 3B Bolognese v3 GGUF?
It depends on the quant: file is 2.1 GB.
What context length does Vezstral 3B Bolognese v3 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.5 GB at 32K.
Where can I download Vezstral 3B Bolognese v3 GGUF?
The files are on Hugging Face in the n1kg0r/Vezstral-3B-Bolognese-v3 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.