Skyfall 36B v2d needs about 25.0 GB of memory at Q4_K_M (a 22.4 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 6 quants, from 13.8 GB (Q2_K) to 39.2 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
Skyfall 36B v2d is a 36.9B-parameter Skyfall model in GGUF format, quantized by BeaverAI. Its trained context length is 32K tokens. The repository has 6 quant files, from 13.8 GB (Q2_K) to 39.2 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 13.8 GB | 16.4 GB | Too big | Get file → | |
| Q3_K_M | 17.9 GB | 20.5 GB | Too big | Get file → | |
| Q4_K_M | 22.4 GB | 25.0 GB | Too big | Get file → | |
| Q5_K_M | 26.2 GB | 28.9 GB | Too big | Get file → | |
| Q6_K | 30.3 GB | 32.9 GB | Too big | Get file → | |
| Q8_0 | 39.2 GB | 41.9 GB | Too big | Get file → |
What GPU do you need for Skyfall 36B v2d?
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 Q3_K_M (17.9 GB file, about 20.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q5_K_M (26.2 GB file, about 28.9 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (39.2 GB file, about 41.9 GB in use).
Which Skyfall 36B v2d quant should you choose?
Q4_K_M is the usual starting point for Skyfall 36B v2d: it balances file size and quality well. Here it is a 22.4 GB file.
The Q8_0 file is 39.2 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 Q2_K at 13.8 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Skyfall 36B v2d
How much VRAM does Skyfall 36B v2d need?
About 25.0 GB at Q4_K_M with an 8K context window. That is the 22.4 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 Skyfall 36B v2d on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 16.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Skyfall 36B v2d GGUF?
It depends on the quant: Q2_K is 13.8 GB, Q3_K_M is 17.9 GB, Q4_K_M is 22.4 GB, Q5_K_M is 26.2 GB, Q6_K is 30.3 GB, Q8_0 is 39.2 GB.
What context length does Skyfall 36B v2d support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download Skyfall 36B v2d GGUF?
The files are on Hugging Face in the BeaverAI/Skyfall-36B-v2d-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.