Minerva 3B base v1.0 needs about 13.5 GB of memory at its main file (a 11.6 GB file) with an 8K context window, so it fits on a 16 GB GPU.
Minerva 3B base v1.0 – a 3‑billion‑parameter language model
Minerva 3B base v1.0 is a 3‑billion‑parameter LLM released under the Apache‑2.0 license. It is available in a single GGUF file with an unknown quantization. The model is designed for general text generation tasks.
Good at
- General language modeling
- Chat and dialogue
- Code generation
Limits
- Requires ~13.5 GB VRAM at 8 k context
- No vision capabilities
- Single‑quant file only
Best for
- Developers building chatbots
- Researchers testing medium‑size models
- Educational projects needing a 3B LLM
Who it’s for. This model is suitable for developers and researchers who need a moderately sized LLM that can run on high‑end GPUs. It is ideal for projects that require a balance between performance and resource usage.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 11.6 GB | 13.5 GB | Too big | Get file → |
The only available GGUF file is unquantized and requires about 13.5 GB of VRAM at 8 k context. If your GPU has at least 14 GB of VRAM, you can run the model directly. For lower‑end GPUs, a custom quantization would be necessary, but no quantized files are provided.
What GPU do you need for Minerva 3B base v1.0?
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: 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 the main file (11.6 GB file, about 13.5 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Minerva 3B base v1.0
How much VRAM does Minerva 3B base v1.0 need?
About 13.5 GB at its main file with an 8K context window. That is the 11.6 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 Minerva 3B base v1.0 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 13.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Minerva 3B base v1.0 GGUF?
It depends on the quant: file is 11.6 GB.
Where can I download Minerva 3B base v1.0 GGUF?
The files are on Hugging Face in the sapienzanlp/Minerva-3B-base-v1.0 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Minerva 3B base v1.0 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.
Can I run Minerva 3B on 8 GB VRAM?
No. The model requires approximately 13.5 GB of VRAM at 8 k context, so 8 GB is insufficient.
Does Minerva 3B support vision tasks?
No. The model has no vision capabilities.
Can I use this model on a CPU?
Yes, but it will be slow and may require a lot of RAM.