z fusion needs about 6.5 GB of memory at Q4_K_S (a 4.8 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 3 quants, from 3.7 GB (Q6_K_XL) to 8.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
z fusion is a 7.62B-parameter Fusion model in GGUF format, quantized by NicRaf. Its trained context length is 40K tokens. The repository has 3 quant files, from 3.7 GB (Q6_K_XL) to 8.7 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K_XL | 3.7 GB | 5.4 GB | Fits | Get file → | |
| Q4_K_S | 4.8 GB | 6.5 GB | Fits | Get file → | |
| Q8_0 | 8.7 GB | 10.4 GB | Too big | Get file → |
What GPU do you need for z fusion?
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 Q6_K_XL (3.7 GB file, about 5.4 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_K_S (4.8 GB file, about 6.5 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.4 GB in use).
Which z fusion quant should you choose?
Q4_K_S (4.8 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is Q6_K_XL at 3.7 GB, with the quality trade-offs that come with fewer bits. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about z fusion
How much VRAM does z fusion need?
About 6.5 GB at Q4_K_S with an 8K context window. That is the 4.8 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 z fusion on an 8 GB GPU?
Yes, with Q4_K_S: the 4.8 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of z fusion GGUF?
It depends on the quant: Q6_K_XL is 3.7 GB, Q4_K_S is 4.8 GB, Q8_0 is 8.7 GB.
What context length does z fusion support?
The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.
Where can I download z fusion GGUF?
The files are on Hugging Face in the NicRaf/z-fusion repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.