TH

TheDrummer Skyfall 31B v4.1 Heretic Clear

ThedrummerGGUF by mradermacherUpdated 2026-02-13
Download on Hugging Face
Parameters31.4B
Context128K
Layers54
Architecturellama
Smallest quant0.0 GB
Quick answer

TheDrummer Skyfall 31B v4.1 Heretic Clear 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 24 quants, from 0.0 GB to 25.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 7.2 GB.

31B‑parameter llama model with reduced refusal behavior

TheDrummer Skyfall 31B v4.1 Heretic Clear is a 31.4B‑parameter llama model fine‑tuned with the Heretic methodology. It is released under Apache‑2.0 and supports roleplay. The model is experimental and still in beta.

Good at

  • Low refusal rates
  • High coherence
  • Roleplay scenarios

Limits

  • Experimental, beta status
  • No vision support
  • Large memory footprint for higher quants

Best for

  • Research on refusal mitigation
  • Testing vector‑based interventions
  • Fine‑tuning for roleplay applications

Who it’s for. Researchers and developers interested in exploring aggressive refusal reduction techniques. Use with caution as the model is still in testing.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.3 GB
Fits Get file →
IQ1_S6.9 GB 9.2 GB
Too big Get file →
IQ1_M7.5 GB 9.8 GB
Too big Get file →
IQ2_XXS8.6 GB 10.9 GB
Too big Get file →
IQ2_XS9.5 GB 11.8 GB
Too big Get file →
IQ2_S9.8 GB 12.1 GB
Too big Get file →
IQ2_M10.7 GB 13.0 GB
Too big Get file →
Q2_K_S10.9 GB 13.2 GB
Too big Get file →
Q2_K11.7 GB 14.0 GB
Too big Get file →
IQ3_XXS12.3 GB 14.6 GB
Too big Get file →
IQ3_XS13.1 GB 15.4 GB
Too big Get file →
Q3_K_S13.7 GB 16.1 GB
Too big Get file →
IQ3_S13.8 GB 16.1 GB
Too big Get file →
IQ3_M14.1 GB 16.4 GB
Too big Get file →
Q3_K_M15.2 GB 17.5 GB
Too big Get file →
Q3_K_L16.4 GB 18.8 GB
Too big Get file →
IQ4_XS16.9 GB 19.2 GB
Too big Get file →
Q4_017.9 GB 20.2 GB
Too big Get file →
Q4_K_S17.9 GB 20.3 GB
Too big Get file →
Q4_K_M19.0 GB 21.3 GB
Too big Get file →
Q4_119.7 GB 22.0 GB
Too big Get file →
Q5_K_S21.7 GB 24.0 GB
Too big Get file →
Q5_K_M22.3 GB 24.6 GB
Too big Get file →
Q6_K25.7 GB 28.0 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (6.86 GB file, 9.2 GB memory). For 12 GB VRAM, IQ2_XS (9.48 GB file, 11.8 GB memory). For 16 GB VRAM, Q4_K_M (18.98 GB file, 21.3 GB memory). Memory estimates are approximate.

What GPU do you need for TheDrummer Skyfall 31B v4.1 Heretic Clear?

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 (25.7 GB file, about 28.0 GB in use).

Which TheDrummer Skyfall 31B v4.1 Heretic Clear quant should you choose?

Q4_K_M is the usual starting point for TheDrummer Skyfall 31B v4.1 Heretic Clear: it balances file size and quality well. Here it is a 19.0 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

Architecturellama
Parameters31.4B
Layers54
Trained context131,072 tokens
KV cache (fp16)216 KB per token

Frequently asked questions about TheDrummer Skyfall 31B v4.1 Heretic Clear

How much VRAM does TheDrummer Skyfall 31B v4.1 Heretic Clear 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 TheDrummer Skyfall 31B v4.1 Heretic Clear 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 TheDrummer Skyfall 31B v4.1 Heretic Clear GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 6.9 GB, IQ1_M is 7.5 GB, IQ2_XXS is 8.6 GB, IQ2_XS is 9.5 GB, IQ2_S is 9.8 GB and 18 more.

What context length does TheDrummer Skyfall 31B v4.1 Heretic Clear 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 TheDrummer Skyfall 31B v4.1 Heretic Clear GGUF?

The files are on Hugging Face in the mradermacher/TheDrummer-Skyfall-31B-v4.1-Heretic-Clear-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 TheDrummer Skyfall 31B v4.1 Heretic Clear use?

Hugging Face lists the license as apache-2.0. 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 this model on 8 GB VRAM?

Yes, using the IQ1_S quant which requires about 9.2 GB of VRAM at 8 k context.

Is this model suitable for production use?

No, it is experimental and in beta; use with caution for research purposes.

What license does it use?

Apache‑2.0, allowing modification and redistribution.

Other GGUFs of TheDrummer-Skyfall-31B-v4.1-Heretic-Clear

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Thedrummer models

All Thedrummer →

Other medium models

All medium models →