Goetia 26B A4B v1.4 LazyLora heresy needs about 17.0 GB of memory at MXFP4_MOE (a 14.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 0.1 GB to 50.5 GB (BF16).
Goetia 26B A4B v1.4 LazyLora heresy is a 25.2B-parameter Goetia model in GGUF format, quantized by MuXodious. Its trained context length is 256K tokens. The repository has 5 quant files, from 0.1 GB to 50.5 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 0.6 GB | Fits | Get file → | |
| IQ4_NL | 14.4 GB | 16.7 GB | Too big | Get file → | |
| MXFP4_MOE | 14.7 GB | 17.0 GB | Too big | Get file → | |
| Q6_K | 22.6 GB | 25.9 GB | Too big | Get file → | |
| BF16 | 50.5 GB | 57.1 GB | Too big | Get file → |
What GPU do you need for Goetia 26B A4B v1.4 LazyLora heresy?
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: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
- 24 GB VRAM: the best quant that fits is MXFP4_MOE (14.7 GB file, about 17.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (22.6 GB file, about 25.9 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (22.6 GB file, about 25.9 GB in use).
Which Goetia 26B A4B v1.4 LazyLora heresy quant should you choose?
MXFP4_MOE (14.7 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.
If memory is tight, the smallest file is the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Goetia 26B A4B v1.4 LazyLora heresy
How much VRAM does Goetia 26B A4B v1.4 LazyLora heresy need?
About 17.0 GB at MXFP4_MOE with an 8K context window. That is the 14.7 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 Goetia 26B A4B v1.4 LazyLora heresy on an 8 GB GPU?
Yes, with the smaller files: the 0.1 GB file needs about 0.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Goetia 26B A4B v1.4 LazyLora heresy GGUF?
It depends on the quant: file is 0.1 GB, IQ4_NL is 14.4 GB, MXFP4_MOE is 14.7 GB, Q6_K is 22.6 GB, BF16 is 50.5 GB.
What context length does Goetia 26B A4B v1.4 LazyLora heresy support?
The GGUF header lists a trained context length of 262,144 tokens (256K).
Where can I download Goetia 26B A4B v1.4 LazyLora heresy GGUF?
The files are on Hugging Face in the MuXodious/Goetia-26B-A4B-v1.4-LazyLora-heresy-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.