BlackBox Coder 3B needs about 4.1 GB of memory at its main file (a 3.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 3.3 GB to 12.3 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.
BlackBox Coder 3B is a 3.09B-parameter Blackbox model in GGUF format, quantized by hodza. Its trained context length is 32K tokens. The repository has 2 quant files, from 3.3 GB to 12.3 GB (F32).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 3.3 GB | 4.1 GB | Fits | Get file → | |
| F32 | 12.3 GB | 13.2 GB | Too big | Get file → |
What GPU do you need for BlackBox Coder 3B?
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: the best quant that fits is the main file (3.3 GB file, about 4.1 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (3.3 GB file, about 4.1 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (3.3 GB file, about 4.1 GB in use).
- 16 GB VRAM: the best quant that fits is F32 (12.3 GB file, about 13.2 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about BlackBox Coder 3B
How much VRAM does BlackBox Coder 3B need?
About 4.1 GB at its main file with an 8K context window. That is the 3.3 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 BlackBox Coder 3B on an 8 GB GPU?
Yes, with the smaller files: the 3.3 GB file needs about 4.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of BlackBox Coder 3B GGUF?
It depends on the quant: file is 3.3 GB, F32 is 12.3 GB.
What context length does BlackBox Coder 3B support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.2 GB at 32K.
Where can I download BlackBox Coder 3B GGUF?
The files are on Hugging Face in the hodza/BlackBox-Coder-3B-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 BlackBox Coder 3B use?
Hugging Face lists the license as bsd-2-clause. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.