Skyfall 31B v4 needs about 21.3 GB of memory at Q4_K_M (a 19.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 28 quants, from 0.0 GB to 62.7 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 7.2 GB.
Skyfall 31B v4 – a 31.4 billion‑parameter llama model
Skyfall 31B v4 is a 31.4 billion‑parameter llama model tuned for creative writing and interactive storytelling. It supports a context length of 131072 tokens and offers a range of quantizations for different memory budgets.
Good at
- Creative text generation
- Interactive storytelling
- Non‑censored responses
Limits
- No vision support
- License not specified
- Large context requires significant VRAM
Best for
- Writing fiction or poetry
- Chatbot development
- Content generation for games
Who it’s for. Developers and content creators seeking a large, creative language model. The model is suitable for those who can allocate sufficient GPU memory and are comfortable with llama.cpp or similar runtimes.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 2.3 GB | Fits | Get file → | |
| IQ2_XXS | 8.6 GB | 10.9 GB | Too big | Get file → | |
| IQ2_XS | 9.5 GB | 11.8 GB | Too big | Get file → | |
| IQ2_S | 9.8 GB | 12.1 GB | Too big | Get file → | |
| IQ2_M | 10.7 GB | 13.0 GB | Too big | Get file → | |
| Q2_K | 11.7 GB | 14.0 GB | Too big | Get file → | |
| IQ3_XXS | 12.3 GB | 14.6 GB | Too big | Get file → | |
| Q2_K_L | 12.4 GB | 14.7 GB | Too big | Get file → | |
| IQ3_XS | 13.1 GB | 15.4 GB | Too big | Get file → | |
| Q3_K_S | 13.7 GB | 16.1 GB | Too big | Get file → | |
| IQ3_M | 14.1 GB | 16.4 GB | Too big | Get file → | |
| Q3_K_M | 15.2 GB | 17.5 GB | Too big | Get file → | |
| Q3_K_L | 16.4 GB | 18.8 GB | Too big | Get file → | |
| IQ4_XS | 16.9 GB | 19.2 GB | Too big | Get file → | |
| Q3_K_XL | 17.0 GB | 19.3 GB | Too big | Get file → | |
| IQ4_NL | 17.9 GB | 20.2 GB | Too big | Get file → | |
| Q4_0 | 17.9 GB | 20.2 GB | Too big | Get file → | |
| Q4_K_S | 17.9 GB | 20.3 GB | Too big | Get file → | |
| Q4_K_M | 19.0 GB | 21.3 GB | Too big | Get file → | |
| Q4_K_L | 19.5 GB | 21.8 GB | Too big | Get file → | |
| Q4_1 | 19.7 GB | 22.0 GB | Too big | Get file → | |
| Q5_K_S | 21.7 GB | 24.0 GB | Too big | Get file → | |
| Q5_K_M | 22.3 GB | 24.6 GB | Too big | Get file → | |
| Q5_K_L | 22.7 GB | 25.0 GB | Too big | Get file → | |
| Q6_K | 25.7 GB | 28.0 GB | Too big | Get file → | |
| Q6_K_L | 26.1 GB | 28.4 GB | Too big | Get file → | |
| Q8_0 | 33.3 GB | 35.6 GB | Too big | Get file → | |
| BF16 | 62.7 GB (2 parts) | 65.0 GB | Too big | Get file → |
For 8 GB VRAM use IQ2_XXS (8.59 GB file, 10.9 GB memory). For 16 GB VRAM use Q3_K_S (13.74 GB file, 16.1 GB memory). For 32 GB VRAM use Q5_K_M (22.25 GB file, 24.6 GB memory).
What GPU do you need for Skyfall 31B v4?
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 the main file (0.0 GB file, about 2.3 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.3 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.3 GB in use).
- 12 GB VRAM: the best quant that fits is IQ2_XS (9.5 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_XS (13.1 GB file, about 15.4 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_S (21.7 GB file, about 24.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K_L (26.1 GB file, about 28.4 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (33.3 GB file, about 35.6 GB in use).
Which Skyfall 31B v4 quant should you choose?
Q4_K_M is the usual starting point for Skyfall 31B v4: it balances file size and quality well. Here it is a 19.0 GB file.
The Q8_0 file is 33.3 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
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 Skyfall 31B v4
How much VRAM does Skyfall 31B v4 need?
About 21.3 GB at Q4_K_M with an 8K context window. That is the 19.0 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 Skyfall 31B v4 on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 2.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Skyfall 31B v4 GGUF?
It depends on the quant: file is 0.0 GB, IQ2_XXS is 8.6 GB, IQ2_XS is 9.5 GB, IQ2_S is 9.8 GB, IQ2_M is 10.7 GB, Q2_K is 11.7 GB and 22 more.
What context length does Skyfall 31B v4 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.8 GB at 8K and 7.2 GB at 32K.
Where can I download Skyfall 31B v4 GGUF?
The files are on Hugging Face in the bartowski/TheDrummer_Skyfall-31B-v4-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run Skyfall 31B v4 on 8 GB VRAM?
Use the IQ2_XXS quantization; it requires 10.9 GB memory at 8 k context, which is close to 8 GB but may need swapping.
Does the model support image input?
No, Skyfall 31B v4 has no vision capabilities.
What runtime can I use to run this model?
Run it with llama.cpp, LM Studio, or any llama.cpp‑based project.