Luna 7B A4B PaperWitch Heresy needs about 5.8 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 25 quants, from 0.0 GB to 5.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
Luna 7B A4B PaperWitch Heresy – a 6.71B MoE conversational model
Luna 7B A4B PaperWitch Heresy is a 6.71B parameter model with 4B active MoE parameters. It is fine‑tuned for immersive roleplay and natural chat, and also trained on math, code and tool‑calling tasks.
Good at
- Roleplay and character dialogue
- Reasoning and problem solving
- Tool‑calling and agent tasks
Limits
- Requires 262144 token context
- No vision support
- MIT license limits commercial use only if modified
Best for
- Creative writing and storytelling
- Interactive roleplay sessions
- Agent‑based tool usage
Who it’s for. Developers and hobbyists who need a conversational model that excels in roleplay and can handle reasoning and tool‑calling. The model is suitable for building chatbots, writing assistants, or agent applications.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.7 GB | Fits | Get file → | |
| IQ1_S | 1.6 GB | 3.3 GB | Fits | Get file → | |
| IQ1_M | 1.7 GB | 3.4 GB | Fits | Get file → | |
| IQ2_XXS | 1.9 GB | 3.7 GB | Fits | Get file → | |
| IQ2_XS | 2.1 GB | 3.8 GB | Fits | Get file → | |
| IQ2_S | 2.2 GB | 3.9 GB | Fits | Get file → | |
| IQ2_M | 2.4 GB | 4.1 GB | Fits | Get file → | |
| Q2_K_S | 2.5 GB | 4.2 GB | Fits | Get file → | |
| Q2_K | 2.6 GB | 4.4 GB | Fits | Get file → | |
| IQ3_XXS | 2.7 GB | 4.4 GB | Fits | Get file → | |
| IQ3_XS | 2.9 GB | 4.6 GB | Fits | Get file → | |
| Q3_K_S | 3.0 GB | 4.8 GB | Fits | Get file → | |
| IQ3_S | 3.1 GB | 4.8 GB | Fits | Get file → | |
| IQ3_M | 3.1 GB | 4.8 GB | Fits | Get file → | |
| Q3_K_M | 3.4 GB | 5.1 GB | Fits | Get file → | |
| Q3_K_L | 3.6 GB | 5.3 GB | Fits | Get file → | |
| IQ4_XS | 3.7 GB | 5.4 GB | Fits | Get file → | |
| IQ4_NL | 3.9 GB | 5.6 GB | Fits | Get file → | |
| Q4_0 | 3.9 GB | 5.6 GB | Fits | Get file → | |
| Q4_K_S | 3.9 GB | 5.6 GB | Fits | Get file → | |
| Q4_K_M | 4.1 GB | 5.8 GB | Fits | Get file → | |
| Q4_1 | 4.3 GB | 6.0 GB | Fits | Get file → | |
| Q5_K_S | 4.7 GB | 6.4 GB | Fits | Get file → | |
| Q5_K_M | 4.8 GB | 6.5 GB | Fits | Get file → | |
| Q6_K | 5.5 GB | 7.2 GB | Tight | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 4.13 GB, estimated 5.8 GB memory). For 12 GB VRAM, Q5_K_M (4.8 GB, 6.5 GB memory) or Q6_K (5.51 GB, 7.2 GB memory) are suitable. For 4 GB VRAM, IQ1_S (1.59 GB, 3.3 GB memory) or IQ1_M (1.73 GB, 3.4 GB memory) are recommended.
What GPU do you need for Luna 7B A4B PaperWitch Heresy?
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: the best quant that fits is IQ2_S (2.2 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_1 (4.3 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (5.5 GB file, about 7.2 GB in use).
Which Luna 7B A4B PaperWitch Heresy quant should you choose?
Q4_K_M is the usual starting point for Luna 7B A4B PaperWitch Heresy: it balances file size and quality well. Here it is a 4.1 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 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 Luna 7B A4B PaperWitch Heresy
How much VRAM does Luna 7B A4B PaperWitch Heresy need?
About 5.8 GB at Q4_K_M with an 8K context window. That is the 4.1 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 Luna 7B A4B PaperWitch Heresy on an 8 GB GPU?
Yes, with Q6_K: the 5.5 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Luna 7B A4B PaperWitch Heresy GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 1.6 GB, IQ1_M is 1.7 GB, IQ2_XXS is 1.9 GB, IQ2_XS is 2.1 GB, IQ2_S is 2.2 GB and 19 more.
What context length does Luna 7B A4B PaperWitch Heresy support?
The GGUF header lists a trained context length of 262,144 tokens (256K). 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 Luna 7B A4B PaperWitch Heresy GGUF?
The files are on Hugging Face in the mradermacher/Luna-7B-A4B-PaperWitch-heresy-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 Luna 7B A4B PaperWitch Heresy use?
Hugging Face lists the license as mit. 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 Luna 7B A4B on 8 GB VRAM?
Yes, using the Q4_K_M quant will fit within 8 GB VRAM with an estimated 5.8 GB memory usage.
Does this model support vision?
No, the model has no vision capabilities.
What license does it use?
The model is released under the MIT license.