SK

Skyfall 36B V2A

SkyfallGGUF by TheDrummerUpdated 2025-02-19
Download on Hugging Face
Parameters36.9B
Context32K
Layers64
Architecturellama
Smallest quant13.8 GB
Quick answer

Skyfall 36B V2A 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 7 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 V2A – a 36.9B llama model with 32,768 token context

Skyfall 36B V2A is a 36.9B parameter llama architecture model. It supports a 32,768 token context window and is available in several GGUF quantizations. The model is designed for creative writing, instruction following, and chain‑of‑thought reasoning.

Good at

  • Creative writing
  • Instruction following
  • Chain‑of‑thought reasoning

Limits

  • No vision support
  • License type is other
  • Requires large VRAM for higher quants

Best for

  • Long‑form storytelling
  • Complex instruction tasks
  • Mathematical reasoning

Who it’s for. Users who need a large language model for detailed creative content or advanced instruction tasks. Suitable for developers running locally with sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K13.8 GB 16.4 GB
Too big Get file →
Q3_K_M17.9 GB 20.5 GB
Too big Get file →
Q4_K_S21.1 GB 23.8 GB
Too big Get file →
Q4_K_M22.4 GB 25.0 GB
Too big Get file →
Q5_K_M26.2 GB 28.9 GB
Too big Get file →
Q6_K30.3 GB 32.9 GB
Too big Get file →
Q8_039.2 GB 41.9 GB
Too big Get file →

For 8 GB VRAM use Q2_K (13.76 GB, ~16.4 GB memory). For 12 GB VRAM use Q3_K_M (17.87 GB, ~20.5 GB memory). For 16 GB VRAM use Q4_K_M (22.37 GB, ~25 GB memory).

What GPU do you need for Skyfall 36B V2A?

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 Q4_K_S (21.1 GB file, about 23.8 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 V2A quant should you choose?

Q4_K_M is the usual starting point for Skyfall 36B V2A: 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

Architecturellama
Parameters36.9B
Layers64
Trained context32,768 tokens
KV cache (fp16)256 KB per token

Source

Quantized byTheDrummer
FamilySkyfall
Licenseother
Downloads (HF)1,356
Last updated2025-02-19

Frequently asked questions about Skyfall 36B V2A

How much VRAM does Skyfall 36B V2A 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 V2A 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 V2A GGUF?

It depends on the quant: Q2_K is 13.8 GB, Q3_K_M is 17.9 GB, Q4_K_S is 21.1 GB, Q4_K_M is 22.4 GB, Q5_K_M is 26.2 GB, Q6_K is 30.3 GB and 1 more.

What context length does Skyfall 36B V2A 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 V2A GGUF?

The files are on Hugging Face in the TheDrummer/Skyfall-36B-v2-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 Skyfall 36B V2A use?

Hugging Face lists the license as other. 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 Skyfall 36B V2A on 8 GB VRAM?

Use the Q2_K quantization; it requires about 16.4 GB memory at 8 k context, so 8 GB VRAM is insufficient.

Does the model support vision tasks?

No, Skyfall 36B V2A does not have vision capabilities.

What is the maximum context length?

The model supports a 32,768 token context window.

Similar models

Browse all →

More from TheDrummer

All by TheDrummer →

More Skyfall models

All Skyfall →

Other large models

All large models →