HO

K2 Horizon 32B Heretic

HorizonGGUF by mradermacherUpdated 2026-10-15
Download on Hugging Face
Parameters34.8B
Context512K
Layers64
Architecturek2-horizon
Smallest quant0.0 GB
Quick answer

K2 Horizon 32B Heretic needs about 23.7 GB of memory at Q4_K_M (a 21.1 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 28.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

K2 Horizon 32B Heretic – 32‑billion‑parameter coding‑focused model

K2 Horizon 32B Heretic is a 32‑billion‑parameter model based on the K2‑Horizon architecture. It is a refusal‑attenuated derivative of IFM/K2‑Horizon‑32B, with BF16 weights and a small code patch to return hidden states. The model is available in multiple GGUF quantizations.

Good at

  • Coding assistance
  • Large context handling
  • Fine‑tuned refusal attenuation

Limits

  • Requires ~70 GB VRAM for full precision
  • No vision support
  • License is Apache‑2.0

Best for

  • Developers needing large‑context code generation
  • Researchers testing refusal‑attenuation
  • Users with limited VRAM using GGUF

Who it’s for. Engineers and researchers who need a large‑parameter model for code generation and want to run it on consumer hardware with GGUF quantizations. The model is suitable for those who can handle the 70 GB VRAM requirement for full‑precision inference.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.7 GB
Fits Get file →
IQ1_S8.0 GB 10.7 GB
Too big Get file →
IQ1_M8.7 GB 11.4 GB
Too big Get file →
IQ2_XXS9.8 GB 12.4 GB
Too big Get file →
IQ2_XS10.8 GB 13.4 GB
Too big Get file →
IQ2_S11.4 GB 14.0 GB
Too big Get file →
IQ2_M12.3 GB 14.9 GB
Too big Get file →
Q2_K_S12.4 GB 15.0 GB
Too big Get file →
Q2_K13.3 GB 15.9 GB
Too big Get file →
IQ3_XXS13.8 GB 16.4 GB
Too big Get file →
IQ3_XS14.7 GB 17.4 GB
Too big Get file →
Q3_K_S15.5 GB 18.1 GB
Too big Get file →
IQ3_S15.5 GB 18.2 GB
Too big Get file →
IQ3_M16.0 GB 18.7 GB
Too big Get file →
Q3_K_M17.1 GB 19.7 GB
Too big Get file →
Q3_K_L18.5 GB 21.1 GB
Too big Get file →
IQ4_XS18.9 GB 21.6 GB
Too big Get file →
Q4_020.0 GB 22.6 GB
Too big Get file →
Q4_K_S20.0 GB 22.7 GB
Too big Get file →
Q4_K_M21.1 GB 23.7 GB
Too big Get file →
Q4_122.0 GB 24.6 GB
Too big Get file →
Q5_K_S24.1 GB 26.7 GB
Too big Get file →
Q5_K_M24.7 GB 27.3 GB
Too big Get file →
Q6_K28.5 GB 31.2 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (12.39 GB file, ~15 GB memory at 8k context). For 16 GB VRAM, Q4_K_S (20.05 GB file, ~22.7 GB memory) or Q4_0 (19.98 GB file, ~22.6 GB memory). For 24 GB VRAM, Q3_K_M (17.09 GB file, ~19.7 GB memory) offers a balance of size and performance. Memory estimates are approximate.

What GPU do you need for K2 Horizon 32B 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 the main file (0.0 GB file, about 2.7 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ1_M (8.7 GB file, about 11.4 GB in use).
  • 16 GB VRAM: the best quant that fits is Q2_K (13.3 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (21.1 GB file, about 23.7 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (28.5 GB file, about 31.2 GB in use).

Which K2 Horizon 32B Heretic quant should you choose?

Q4_K_M is the usual starting point for K2 Horizon 32B Heretic: it balances file size and quality well. Here it is a 21.1 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
Parameters34.8B
Layers64
Trained context524,288 tokens
KV cache (fp16)256 KB per token

Source

Quantized bymradermacher
FamilyHorizon
Licenseapache-2.0
Downloads (HF)5,798
Last updated2026-10-15

Frequently asked questions about K2 Horizon 32B Heretic

How much VRAM does K2 Horizon 32B Heretic need?

About 23.7 GB at Q4_K_M with an 8K context window. That is the 21.1 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 32B Heretic on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of K2 Horizon 32B Heretic GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 8.0 GB, IQ1_M is 8.7 GB, IQ2_XXS is 9.8 GB, IQ2_XS is 10.8 GB, IQ2_S is 11.4 GB and 18 more.

What context length does K2 Horizon 32B 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 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download K2 Horizon 32B Heretic GGUF?

The files are on Hugging Face in the mradermacher/K2-Horizon-32B-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 32B 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 32B Heretic on 8 GB VRAM?

Use the Q4_K_M GGUF quant; it requires about 15 GB of VRAM at 8k context, which is close to 8 GB but may need swapping or lower context.

Does the model support image inputs?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of K2-Horizon-32B-heretic

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Horizon models

All Horizon →

Other large models

All large models →