HO

K2 Horizon 3.7B Heretic

HorizonGGUF by mradermacherUpdated 2026-10-14
Download on Hugging Face
Parameters5.06B
Context512K
Layers36
Architecturek2-horizon
Smallest quant0.0 GB
Quick answer

K2 Horizon 3.7B Heretic needs about 4.9 GB of memory at Q4_K_M (a 3.2 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 25 quants, from 0.0 GB to 4.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

K2 Horizon 3.7B Heretic – a 5.06B parameter model with ablation‑removed refusals

K2 Horizon 3.7B Heretic is a 5.06B parameter model based on the Horizon family. It removes refusal behaviour through in‑layer ablation while preserving normal functionality. The model is released under Apache‑2.0 and is available in multiple GGUF quantisations.

Good at

  • Ablation‑removed refusal behaviour
  • Maintains factual Q&A and creative tasks
  • Supports chat templates

Limits

  • Large context size of 524288 tokens
  • Requires significant VRAM for higher‑quality quants
  • No vision or multimodal support

Best for

  • Chat‑based applications needing safe responses
  • Research on refusal mitigation
  • Deployments on systems with 8 GB+ VRAM

Who it’s for. Developers and researchers who need a large language model that has had refusal behaviour ablated. The model is suitable for applications where safety behaviour is desired but not overly restrictive.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.7 GB
Fits Get file →
IQ1_S1.5 GB 3.2 GB
Fits Get file →
IQ1_M1.5 GB 3.3 GB
Fits Get file →
IQ2_XXS1.7 GB 3.4 GB
Fits Get file →
IQ2_XS1.8 GB 3.5 GB
Fits Get file →
IQ2_S1.9 GB 3.6 GB
Fits Get file →
IQ2_M2.0 GB 3.7 GB
Fits Get file →
Q2_K_S2.0 GB 3.7 GB
Fits Get file →
Q2_K2.1 GB 3.9 GB
Fits Get file →
IQ3_XXS2.2 GB 3.9 GB
Fits Get file →
IQ3_XS2.4 GB 4.1 GB
Fits Get file →
Q3_K_S2.4 GB 4.1 GB
Fits Get file →
IQ3_S2.4 GB 4.2 GB
Fits Get file →
IQ3_M2.5 GB 4.2 GB
Fits Get file →
Q3_K_M2.6 GB 4.3 GB
Fits Get file →
Q3_K_L2.8 GB 4.5 GB
Fits Get file →
IQ4_XS2.9 GB 4.6 GB
Fits Get file →
Q4_03.0 GB 4.7 GB
Fits Get file →
IQ4_NL3.0 GB 4.7 GB
Fits Get file →
Q4_K_S3.0 GB 4.7 GB
Fits Get file →
Q4_K_M3.2 GB 4.9 GB
Fits Get file →
Q4_13.3 GB 5.0 GB
Fits Get file →
Q5_K_S3.6 GB 5.3 GB
Fits Get file →
Q5_K_M3.6 GB 5.4 GB
Fits Get file →
Q6_K4.2 GB 5.9 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (file size 3.16 GB, memory 4.9 GB). For 12 GB VRAM, Q5_K_M (file size 3.64 GB, memory 5.4 GB). For 16 GB VRAM, Q6_K (file size 4.16 GB, memory 5.9 GB). Estimates are approximate.

What GPU do you need for K2 Horizon 3.7B Heretic?

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 IQ3_XXS (2.2 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (4.2 GB file, about 5.9 GB in use).

Which K2 Horizon 3.7B Heretic quant should you choose?

Q4_K_M is the usual starting point for K2 Horizon 3.7B Heretic: it balances file size and quality well. Here it is a 3.2 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

Architecturek2-horizon
Parameters5.06B
Layers36
Trained context524,288 tokens
KV cache (fp16)144 KB per token

Source

Quantized bymradermacher
FamilyHorizon
Licenseapache-2.0
Downloads (HF)3,322
Last updated2026-10-14

Frequently asked questions about K2 Horizon 3.7B Heretic

How much VRAM does K2 Horizon 3.7B Heretic need?

About 4.9 GB at Q4_K_M with an 8K context window. That is the 3.2 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 K2 Horizon 3.7B Heretic on an 8 GB GPU?

Yes, with Q6_K: the 4.2 GB file needs about 5.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of K2 Horizon 3.7B Heretic GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 1.5 GB, IQ1_M is 1.5 GB, IQ2_XXS is 1.7 GB, IQ2_XS is 1.8 GB, IQ2_S is 1.9 GB and 19 more.

What context length does K2 Horizon 3.7B Heretic support?

The GGUF header lists a trained context length of 524,288 tokens (512K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download K2 Horizon 3.7B Heretic GGUF?

The files are on Hugging Face in the mradermacher/K2-Horizon-3.7B-heretic-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 K2 Horizon 3.7B Heretic 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 K2 Horizon 3.7B Heretic on 8 GB VRAM?

Yes, using the Q4_K_M quant which requires about 4.9 GB of VRAM at 8 k context.

Does the model support vision or multimodal inputs?

No, the model is purely text‑only and has no vision support.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of K2-Horizon-3.7B-heretic

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Horizon models

All Horizon →

Other small models

All small models →