SK

Skyfall 39B V1A WS

SkyfallGGUF by bartowskiUpdated 2024-12-15
Download on Hugging Face
Parameters39B
Context128K
Layers99
Architecturellama
Smallest quant10.4 GB
Quick answer

Skyfall 39B V1A WS needs about 27.2 GB of memory at Q4_K_M (a 23.4 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 25 quants, from 10.4 GB (IQ2_XXS) to 78.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 13.3 GB.

Skyfall 39B V1A WS – a 39B llama model with tool use support

Skyfall 39B V1A WS is a 39‑billion‑parameter llama model fine‑tuned from an experimental upscale of Mistral Small 22B. It supports tool usage and is available in multiple GGUF quantizations. The model was trained on 131072 context tokens.

Good at

  • Tool‑enabled reasoning
  • Large context handling
  • Fine‑tuned for dialogue

Limits

  • No vision support
  • License not specified
  • Requires high VRAM for full precision

Best for

  • Chatbots needing tool integration
  • Long‑form content generation
  • Complex reasoning tasks

Who it’s for. Developers and researchers building AI assistants that require tool use and extended context. The model is suitable for those who can allocate sufficient GPU memory for the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS10.4 GB 14.3 GB
Too big Get file →
IQ2_XS11.6 GB 15.4 GB
Too big Get file →
IQ2_S12.3 GB 16.1 GB
Too big Get file →
IQ2_M13.3 GB 17.1 GB
Too big Get file →
Q2_K14.4 GB 18.3 GB
Too big Get file →
Q2_K_L14.6 GB 18.5 GB
Too big Get file →
IQ3_XS16.0 GB 19.9 GB
Too big Get file →
Q3_K_S16.9 GB 20.7 GB
Too big Get file →
IQ3_M17.6 GB 21.4 GB
Too big Get file →
Q3_K_M18.8 GB 22.7 GB
Too big Get file →
Q3_K_L20.5 GB 24.4 GB
Too big Get file →
Q3_K_XL20.7 GB 24.5 GB
Too big Get file →
IQ4_XS20.9 GB 24.7 GB
Too big Get file →
Q4_022.1 GB 25.9 GB
Too big Get file →
IQ4_NL22.1 GB 25.9 GB
Too big Get file →
Q4_K_S22.2 GB 26.0 GB
Too big Get file →
Q4_K_M23.4 GB 27.2 GB
Too big Get file →
Q4_K_L23.5 GB 27.3 GB
Too big Get file →
Q5_K_S26.9 GB 30.7 GB
Too big Get file →
Q5_K_M27.6 GB 31.4 GB
Too big Get file →
Q5_K_L27.7 GB 31.5 GB
Too big Get file →
Q6_K32.0 GB 35.8 GB
Too big Get file →
Q6_K_L32.1 GB 35.9 GB
Too big Get file →
Q8_041.5 GB 45.3 GB
Too big Get file →
F1678.0 GB (2 parts) 81.9 GB
Too big Get file →

For 8 GB VRAM use IQ2_XXS (10.44 GB file, ~14.3 GB memory at 8 k context). For 16 GB VRAM use Q4_K_M (23.36 GB file, ~27.2 GB memory). For 24 GB VRAM use Q5_K_M (27.55 GB file, ~31.4 GB memory).

What GPU do you need for Skyfall 39B V1A WS?

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: the best quant that fits is IQ2_XS (11.6 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q3_K_M (18.8 GB file, about 22.7 GB in use).
  • 32 GB VRAM: the best quant that fits is Q5_K_L (27.7 GB file, about 31.5 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (41.5 GB file, about 45.3 GB in use).

Which Skyfall 39B V1A WS quant should you choose?

Q4_K_M is the usual starting point for Skyfall 39B V1A WS: it balances file size and quality well. Here it is a 23.4 GB file.

The Q8_0 file is 41.5 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 IQ2_XXS at 10.4 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
Parameters39B
Layers99
Trained context131,072 tokens
KV cache (fp16)396 KB per token

Source

Quantized bybartowski
FamilySkyfall
Downloads (HF)622
Last updated2024-12-15

Frequently asked questions about Skyfall 39B V1A WS

How much VRAM does Skyfall 39B V1A WS need?

About 27.2 GB at Q4_K_M with an 8K context window. That is the 23.4 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 39B V1A WS on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Skyfall 39B V1A WS GGUF?

It depends on the quant: IQ2_XXS is 10.4 GB, IQ2_XS is 11.6 GB, IQ2_S is 12.3 GB, IQ2_M is 13.3 GB, Q2_K is 14.4 GB, Q2_K_L is 14.6 GB and 19 more.

What context length does Skyfall 39B V1A WS support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.3 GB at 8K and 13.3 GB at 32K.

Where can I download Skyfall 39B V1A WS GGUF?

The files are on Hugging Face in the bartowski/Skyfall-39B-v1-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 39B V1A WS on 8 GB VRAM?

Use the IQ2_XXS quantization; it requires about 14.3 GB memory at 8 k context, which is close to 8 GB VRAM but may need CPU fallback.

Does the model support vision?

No, the model does not include vision capabilities.

What is the maximum context length?

The model was trained on 131072 context tokens.

Other GGUFs of Skyfall-39B-v1

Similar models

Browse all →

More from bartowski

All by bartowski →

More Skyfall models

All Skyfall →

Other large models

All large models →