fblgit una cybertron 7b v2 bf16 needs about 4.3 GB of memory at BF16 (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 2.7 GB (BF16) to 3.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
fblgit una cybertron 7b v2 bf16 is a 7.24B-parameter Una model in GGUF format, quantized by tensorblock. Its trained context length is 32K tokens. The repository has 2 quant files, from 2.7 GB (BF16) to 3.5 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 2.7 GB | 4.3 GB | Fits | Get file → | |
| BF16 | 3.5 GB | 5.1 GB | Fits | Get file → |
What GPU do you need for fblgit una cybertron 7b v2 bf16?
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 BF16 (3.5 GB file, about 5.1 GB in use).
Which fblgit una cybertron 7b v2 bf16 quant should you choose?
BF16 (2.7 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about fblgit una cybertron 7b v2 bf16
How much VRAM does fblgit una cybertron 7b v2 bf16 need?
About 4.3 GB at BF16 with an 8K context window. That is the 2.7 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 fblgit una cybertron 7b v2 bf16 on an 8 GB GPU?
Yes, with BF16: the 3.5 GB file needs about 5.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of fblgit una cybertron 7b v2 bf16 GGUF?
It depends on the quant: BF16 is 2.7 GB, BF16 is 3.5 GB.
What context length does fblgit una cybertron 7b v2 bf16 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download fblgit una cybertron 7b v2 bf16 GGUF?
The files are on Hugging Face in the tensorblock/fblgit_una-cybertron-7b-v2-bf16-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 fblgit una cybertron 7b v2 bf16 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.