RedZFUN v6 ZIB Distilled AGILE 8steps needs about 8.6 GB of memory at BF16 (a 7.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 5.0 GB (BF16) to 12.3 GB (BF16).
RedZFUN v6 ZIB Distilled AGILE 8steps is a 6.15B-parameter Redzfun model in GGUF format, quantized by n0kovo. The repository has 3 quant files, from 5.0 GB (BF16) to 12.3 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 5.0 GB | 6.1 GB | Fits | Get file → | |
| BF16 | 7.2 GB | 8.6 GB | Too big | Get file → | |
| BF16 | 12.3 GB | 14.3 GB | Too big | Get file → |
What GPU do you need for RedZFUN v6 ZIB Distilled AGILE 8steps?
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: the best quant that fits is BF16 (5.0 GB file, about 6.1 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (7.2 GB file, about 8.6 GB in use).
- 16 GB VRAM: the best quant that fits is BF16 (12.3 GB file, about 14.3 GB in use).
Which RedZFUN v6 ZIB Distilled AGILE 8steps quant should you choose?
BF16 (7.2 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.
If memory is tight, the smallest file is BF16 at 5.0 GB, with the quality trade-offs that come with fewer bits. 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
Frequently asked questions about RedZFUN v6 ZIB Distilled AGILE 8steps
How much VRAM does RedZFUN v6 ZIB Distilled AGILE 8steps need?
About 8.6 GB at BF16 with an 8K context window. That is the 7.2 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 RedZFUN v6 ZIB Distilled AGILE 8steps on an 8 GB GPU?
Yes, with BF16: the 5.0 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of RedZFUN v6 ZIB Distilled AGILE 8steps GGUF?
It depends on the quant: BF16 is 5.0 GB, BF16 is 7.2 GB, BF16 is 12.3 GB.
Where can I download RedZFUN v6 ZIB Distilled AGILE 8steps GGUF?
The files are on Hugging Face in the n0kovo/RedZFUN-v6-ZIB-Distilled-AGILE-8steps-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.