G4 Moonlight Dusk 26B A4B Heretic needs about 25.8 GB of memory at Q4_K_M (a 17.2 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 23.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.
26B Gemma4 model with roleplay focus
G4 Moonlight Dusk 26B A4B Heretic is a 26‑billion parameter Gemma4 model. It is a mixture of experts with 4 billion active parameters and supports 262 144‑token context. The model is released under Apache‑2.0.
Good at
- Roleplay
- Long‑form storytelling
- Creative writing
Limits
- No vision support
- Large VRAM requirement for full precision
- Requires 8‑bit or higher quantization for practical use
Best for
- Chatbots needing deep context
- Narrative generation
- Role‑playing games
Who it’s for. Developers building conversational agents that need extended context and roleplay capabilities. The model is suitable for applications that can handle the memory demands of a 26‑billion parameter Gemma4 architecture.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 8.6 GB | Too big | Get file → | |
| IQ1_S | 8.5 GB | 17.1 GB | Too big | Get file → | |
| IQ1_M | 8.9 GB | 17.5 GB | Too big | Get file → | |
| IQ2_XXS | 9.5 GB | 18.1 GB | Too big | Get file → | |
| IQ2_XS | 10.1 GB | 18.6 GB | Too big | Get file → | |
| IQ2_S | 10.2 GB | 18.7 GB | Too big | Get file → | |
| IQ2_M | 10.7 GB | 19.2 GB | Too big | Get file → | |
| Q2_K | 10.8 GB | 19.4 GB | Too big | Get file → | |
| Q2_K_S | 10.9 GB | 19.4 GB | Too big | Get file → | |
| IQ3_XXS | 11.6 GB | 20.2 GB | Too big | Get file → | |
| IQ3_XS | 12.0 GB | 20.5 GB | Too big | Get file → | |
| IQ3_S | 12.5 GB | 21.1 GB | Too big | Get file → | |
| Q3_K_S | 12.5 GB | 21.1 GB | Too big | Get file → | |
| IQ3_M | 12.7 GB | 21.3 GB | Too big | Get file → | |
| Q3_K_M | 13.6 GB | 22.2 GB | Too big | Get file → | |
| Q3_K_L | 14.1 GB | 22.7 GB | Too big | Get file → | |
| IQ4_XS | 14.3 GB | 22.9 GB | Too big | Get file → | |
| Q4_0 | 14.9 GB | 23.5 GB | Too big | Get file → | |
| Q4_K_S | 15.9 GB | 24.4 GB | Too big | Get file → | |
| Q4_1 | 16.4 GB | 25.0 GB | Too big | Get file → | |
| Q4_K_M | 17.2 GB | 25.8 GB | Too big | Get file → | |
| Q5_K_S | 18.5 GB | 27.0 GB | Too big | Get file → | |
| Q5_K_M | 19.6 GB | 28.2 GB | Too big | Get file → | |
| Q6_K | 23.2 GB | 31.8 GB | Too big | Get file → |
For 8 GB VRAM use IQ1_S (8.53 GB file, 17.1 GB memory). With 12 GB VRAM IQ2_S (10.19 GB file, 18.7 GB memory) is a good balance. For 16 GB VRAM, Q4_K_M (17.21 GB file, 25.8 GB memory) offers higher quality. Memory estimates are approximate.
What GPU do you need for G4 Moonlight Dusk 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_0 (14.9 GB file, about 23.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (23.2 GB file, about 31.8 GB in use).
Which G4 Moonlight Dusk 26B A4B Heretic quant should you choose?
Q4_K_M is the usual starting point for G4 Moonlight Dusk 26B A4B Heretic: it balances file size and quality well. Here it is a 17.2 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 G4 Moonlight Dusk 26B A4B Heretic
How much VRAM does G4 Moonlight Dusk 26B A4B Heretic need?
About 25.8 GB at Q4_K_M with an 8K context window. That is the 17.2 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 G4 Moonlight Dusk 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 G4 Moonlight Dusk 26B A4B Heretic GGUF?
It depends on the quant: file is 0.1 GB, IQ1_S is 8.5 GB, IQ1_M is 8.9 GB, IQ2_XXS is 9.5 GB, IQ2_XS is 10.1 GB, IQ2_S is 10.2 GB and 18 more.
What context length does G4 Moonlight Dusk 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 G4 Moonlight Dusk 26B A4B Heretic GGUF?
The files are on Hugging Face in the mradermacher/G4-Moonlight-Dusk-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 G4 Moonlight Dusk 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 this model on 8 GB VRAM?
Use the IQ1_S quant, which requires about 17.1 GB of VRAM at 8 k context. It is the smallest quant that works with 8 GB VRAM.
Does this model support vision?
No, the model does not include vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.