Eclipsed Phoenix 26B A4B Heretic needs about 25.3 GB of memory at Q4_K_M (a 16.8 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 24 quants, from 0.1 GB to 22.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.
Eclipsed Phoenix 26B A4B Heretic – a 26B Gemma4 MoE model for roleplay and creative writing
Eclipsed Phoenix 26B A4B Heretic is a 26‑billion‑parameter Gemma4 model with 4 billion active MoE parameters. It was created by modifying the final four MoE expert layers of the parent model, producing distinct prose and stronger subtext. The model is released under Apache‑2.0 and supports long‑form roleplay and storytelling.
Good at
- Roleplay and character dialogue
- Stylized creative writing
- Long‑form narrative continuity
Limits
- Large context size requires high VRAM
- No vision or multimodal support
- Requires GGUF format
Best for
- Interactive fiction with branching scenes
- Worldbuilding and multi‑character plots
- Dialogue‑heavy creative projects
Who it’s for. Developers and writers who need a large, text‑only model for roleplay and creative writing. The model is suitable for local deployment using llama.cpp and requires a compatible GPU with sufficient VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 8.6 GB | Too big | Get file → | |
| IQ1_S | 8.3 GB | 16.8 GB | Too big | Get file → | |
| IQ1_M | 8.7 GB | 17.2 GB | Too big | Get file → | |
| IQ2_XXS | 9.3 GB | 17.9 GB | Too big | Get file → | |
| IQ2_XS | 9.8 GB | 18.4 GB | Too big | Get file → | |
| IQ2_S | 9.9 GB | 18.4 GB | Too big | Get file → | |
| IQ2_M | 10.4 GB | 18.9 GB | Too big | Get file → | |
| Q2_K | 10.6 GB | 19.1 GB | Too big | Get file → | |
| Q2_K_S | 10.6 GB | 19.2 GB | Too big | Get file → | |
| IQ3_XXS | 11.3 GB | 19.9 GB | Too big | Get file → | |
| IQ3_XS | 11.6 GB | 20.2 GB | Too big | Get file → | |
| IQ3_S | 12.2 GB | 20.8 GB | Too big | Get file → | |
| Q3_K_S | 12.2 GB | 20.8 GB | Too big | Get file → | |
| IQ3_M | 12.4 GB | 20.9 GB | Too big | Get file → | |
| Q3_K_M | 13.3 GB | 21.8 GB | Too big | Get file → | |
| Q3_K_L | 13.8 GB | 22.4 GB | Too big | Get file → | |
| IQ4_XS | 13.9 GB | 22.5 GB | Too big | Get file → | |
| Q4_0 | 14.5 GB | 23.0 GB | Too big | Get file → | |
| Q4_K_S | 15.5 GB | 24.0 GB | Too big | Get file → | |
| Q4_1 | 16.0 GB | 24.5 GB | Too big | Get file → | |
| Q4_K_M | 16.8 GB | 25.3 GB | Too big | Get file → | |
| Q5_K_S | 18.0 GB | 26.5 GB | Too big | Get file → | |
| Q5_K_M | 19.1 GB | 27.7 GB | Too big | Get file → | |
| Q6_K | 22.6 GB | 31.2 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (8.29 GB, ~16.8 GB memory at 8k context). With 12 GB VRAM, IQ2_M (10.38 GB, ~18.9 GB memory) or Q2_K (10.58 GB, ~19.1 GB). For 16 GB VRAM, Q4_K_M (16.8 GB, ~25.3 GB memory) or Q5_K_M (19.13 GB, ~27.7 GB memory).
What GPU do you need for Eclipsed Phoenix 26B A4B Heretic?
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: the best quant that fits is the main file (0.1 GB file, about 8.6 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 8.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_S (15.5 GB file, about 24.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (22.6 GB file, about 31.2 GB in use).
Which Eclipsed Phoenix 26B A4B Heretic quant should you choose?
Q4_K_M is the usual starting point for Eclipsed Phoenix 26B A4B Heretic: it balances file size and quality well. Here it is a 16.8 GB file.
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
Source
Frequently asked questions about Eclipsed Phoenix 26B A4B Heretic
How much VRAM does Eclipsed Phoenix 26B A4B Heretic need?
About 25.3 GB at Q4_K_M with an 8K context window. That is the 16.8 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 Eclipsed Phoenix 26B A4B Heretic on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Eclipsed Phoenix 26B A4B Heretic GGUF?
It depends on the quant: file is 0.1 GB, IQ1_S is 8.3 GB, IQ1_M is 8.7 GB, IQ2_XXS is 9.3 GB, IQ2_XS is 9.8 GB, IQ2_S is 9.9 GB and 18 more.
What context length does Eclipsed Phoenix 26B A4B Heretic 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 Eclipsed Phoenix 26B A4B Heretic GGUF?
The files are on Hugging Face in the alexokita/Eclipsed-Phoenix-26B-A4B-Heretic-i1-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 Eclipsed Phoenix 26B A4B Heretic 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.
Can I run Eclipsed Phoenix 26B A4B Heretic on 8 GB VRAM?
Use the IQ1_S quant; it requires about 16.8 GB of VRAM at 8k context, which is close to the limit of an 8 GB GPU. It may run with lower context or with memory swapping.
Does the model support image input?
No, the GGUF files contain only text weights; there is no multimodal support.
What license applies to this model?
The model is released under the Apache‑2.0 license.