LO

Loki V2.0 Heretic Uncensored

LokiGGUF by mradermacherUpdated 2026-05-04
Download on Hugging Face
Parameters70.6B
Context128K
Layers80
Architecturellama
Smallest quant0.0 GB
Quick answer

Loki V2.0 Heretic Uncensored needs about 45.7 GB of memory at Q4_K_M (a 42.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 24 quants, from 0.0 GB to 57.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

70.6B parameter Llama model with reduced refusal mechanisms

Loki V2.0 Heretic Uncensored is a 70.6B parameter Llama model fine‑tuned with the Heretic repository. It is released under apache‑2.0 and supports roleplay and tools. The model is experimental and intended for research into alignment and vector intervention.

Good at

  • Roleplay
  • Tools integration
  • Reduced refusal

Limits

  • Experimental / beta
  • No vision support
  • Large VRAM requirement for higher quants

Best for

  • Research into alignment
  • Creative roleplay
  • Testing vector interventions

Who it’s for. Researchers and developers exploring model alignment and vector-based interventions. Use with caution due to its experimental status.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 3.2 GB
Fits Get file →
IQ1_S15.3 GB 18.5 GB
Too big Get file →
IQ1_M16.8 GB 19.9 GB
Too big Get file →
IQ2_XXS19.1 GB 22.3 GB
Too big Get file →
IQ2_XS21.1 GB 24.3 GB
Too big Get file →
IQ2_S22.2 GB 25.4 GB
Too big Get file →
IQ2_M24.1 GB 27.3 GB
Too big Get file →
Q2_K_S24.5 GB 27.7 GB
Too big Get file →
Q2_K26.4 GB 29.6 GB
Too big Get file →
IQ3_XXS27.5 GB 30.7 GB
Too big Get file →
IQ3_XS29.3 GB 32.5 GB
Too big Get file →
IQ3_S30.9 GB 34.1 GB
Too big Get file →
Q3_K_S30.9 GB 34.1 GB
Too big Get file →
IQ3_M31.9 GB 35.1 GB
Too big Get file →
Q3_K_M34.3 GB 37.5 GB
Too big Get file →
Q3_K_L37.1 GB 40.3 GB
Too big Get file →
IQ4_XS37.9 GB 41.1 GB
Too big Get file →
Q4_040.1 GB 43.3 GB
Too big Get file →
Q4_K_S40.3 GB 43.5 GB
Too big Get file →
Q4_K_M42.5 GB 45.7 GB
Too big Get file →
Q4_144.3 GB 47.5 GB
Too big Get file →
Q5_K_S48.7 GB 51.8 GB
Too big Get file →
Q5_K_M49.9 GB 53.1 GB
Too big Get file →
Q6_K57.9 GB 61.1 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (15.34 GB, 18.5 GB memory) or IQ1_M (16.75 GB, 19.9 GB memory). For 16 GB VRAM, IQ2_S (21.14 GB, 24.3 GB memory) or Q2_K (26.38 GB, 29.6 GB memory) are suitable. Larger VRAM allows higher quality quants such as Q3_K_L (37.14 GB, 40.3 GB memory).

What GPU do you need for Loki V2.0 Heretic Uncensored?

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 3.2 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ2_XXS (19.1 GB file, about 22.3 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ3_XXS (27.5 GB file, about 30.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_1 (44.3 GB file, about 47.5 GB in use).

Which Loki V2.0 Heretic Uncensored quant should you choose?

Q4_K_M is the usual starting point for Loki V2.0 Heretic Uncensored: it balances file size and quality well. Here it is a 42.5 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
Parameters70.6B
Layers80
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyLoki
Licenseapache-2.0
Downloads (HF)842
Last updated2026-05-04

Frequently asked questions about Loki V2.0 Heretic Uncensored

How much VRAM does Loki V2.0 Heretic Uncensored need?

About 45.7 GB at Q4_K_M with an 8K context window. That is the 42.5 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 Loki V2.0 Heretic Uncensored on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 3.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Loki V2.0 Heretic Uncensored GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 15.3 GB, IQ1_M is 16.8 GB, IQ2_XXS is 19.1 GB, IQ2_XS is 21.1 GB, IQ2_S is 22.2 GB and 18 more.

What context length does Loki V2.0 Heretic Uncensored support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download Loki V2.0 Heretic Uncensored GGUF?

The files are on Hugging Face in the mradermacher/Loki-V2.0-Heretic-Uncensored-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 Loki V2.0 Heretic Uncensored 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?

Use the IQ1_S or IQ1_M quant, which require approximately 18.5 GB or 19.9 GB of VRAM at 8 k context.

Does this model support vision?

No, the model does not include vision capabilities.

What license applies to this model?

The model is released under the apache‑2.0 license.

Other GGUFs of Loki-V2.0-Heretic-Uncensored

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Loki models

All Loki →

Other large models

All large models →