Naphula Goetia 26B A4B v1.7 APEX needs about 26.0 GB of memory at Q4_K_M (a 17.4 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 3 quants, from 12.6 GB (Q3_K_S) to 17.4 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.
Naphula Goetia 26B A4B v1.7 APEX – a 26B gemma4 MoE model for roleplay
Naphula Goetia 26B A4B v1.7 APEX is a 26B parameter gemma4 model with 4B active MoE parameters. It is quantized with APEX for llama.cpp and supports a 262144 token context. The model is tailored for roleplaying scenarios.
Good at
- Roleplay narratives
- Large context handling
- MoE efficiency
Limits
- No vision support
- License is gemma
- Large VRAM requirement
Best for
- Interactive fiction
- Chatbot roleplay
- Narrative generation
Who it’s for. Developers and hobbyists who need a large‑parameter roleplay model with extended context. The model is suitable for users with sufficient GPU memory and who are comfortable with llama.cpp quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 12.6 GB | 21.1 GB | Too big | Get file → | |
| IQ4_XS | 14.7 GB | 23.2 GB | Too big | Get file → | |
| Q4_K_M | 17.4 GB | 26.0 GB | Too big | Get file → |
For 8 GB VRAM, use Q3_K_S (12.59 GB, ~21.1 GB memory at 8 k context). For 12 GB VRAM, Q4_K_M (17.41 GB, ~26 GB memory) offers better quality. IQ4_XS (14.66 GB, ~23.2 GB memory) is a middle ground.
What GPU do you need for Naphula Goetia 26B A4B v1.7 APEX?
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: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is IQ4_XS (14.7 GB file, about 23.2 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K_M (17.4 GB file, about 26.0 GB in use).
Which Naphula Goetia 26B A4B v1.7 APEX quant should you choose?
Q4_K_M is the usual starting point for Naphula Goetia 26B A4B v1.7 APEX: it balances file size and quality well. Here it is a 17.4 GB file.
If memory is tight, the smallest file is Q3_K_S at 12.6 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Naphula Goetia 26B A4B v1.7 APEX
How much VRAM does Naphula Goetia 26B A4B v1.7 APEX need?
About 26.0 GB at Q4_K_M with an 8K context window. That is the 17.4 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 Naphula Goetia 26B A4B v1.7 APEX on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 21.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Naphula Goetia 26B A4B v1.7 APEX GGUF?
It depends on the quant: Q3_K_S is 12.6 GB, IQ4_XS is 14.7 GB, Q4_K_M is 17.4 GB.
What context length does Naphula Goetia 26B A4B v1.7 APEX support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 8.1 GB at 8K and 32.2 GB at 32K.
Where can I download Naphula Goetia 26B A4B v1.7 APEX GGUF?
The files are on Hugging Face in the Koshkasa/Naphula_Goetia-26B-A4B-v1.7-APEX-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 Naphula Goetia 26B A4B v1.7 APEX use?
Hugging Face lists the license as gemma. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run this model on 8 GB VRAM?
Use the Q3_K_S quantization; it requires about 21.1 GB memory at 8 k context, which exceeds 8 GB VRAM, so it is not feasible.
Does this model support vision?
No, the model has no vision capabilities.
What is the context length?
The model supports a context length of 262144 tokens.