K2 Horizon 0.9B Heretic needs about 1.6 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 0.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.
K2 Horizon 0.9B Heretic – 1.08B parameter LLM with refusal ablation
K2 Horizon 0.9B Heretic is a 1.08B parameter model based on the K2-Horizon architecture. It removes refusal behaviour through in‑layer ablation while preserving factual accuracy. The model supports a 131072 token context window and is released under Apache‑2.0.
Good at
- Refusal‑free responses
- Factual Q&A
- Chat template compatibility
Limits
- No vision support
- Requires 8‑k context for memory estimates
- License is Apache‑2.0
Best for
- Chatbots needing safe output
- Research on refusal ablation
- Low‑memory inference
Who it’s for. Developers and researchers who need a small, refusal‑ablated LLM for local deployment. The model is suitable for edge devices with limited VRAM and for experiments in safety research.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.0 GB | Fits | Get file → | |
| IQ1_S | 0.3 GB | 1.3 GB | Fits | Get file → | |
| IQ1_M | 0.3 GB | 1.3 GB | Fits | Get file → | |
| IQ2_XXS | 0.3 GB | 1.3 GB | Fits | Get file → | |
| IQ2_XS | 0.4 GB | 1.3 GB | Fits | Get file → | |
| IQ2_S | 0.4 GB | 1.4 GB | Fits | Get file → | |
| IQ2_M | 0.4 GB | 1.4 GB | Fits | Get file → | |
| Q2_K_S | 0.4 GB | 1.4 GB | Fits | Get file → | |
| Q2_K | 0.4 GB | 1.4 GB | Fits | Get file → | |
| IQ3_XXS | 0.5 GB | 1.4 GB | Fits | Get file → | |
| IQ3_XS | 0.5 GB | 1.5 GB | Fits | Get file → | |
| Q3_K_S | 0.5 GB | 1.5 GB | Fits | Get file → | |
| IQ3_S | 0.5 GB | 1.5 GB | Fits | Get file → | |
| IQ3_M | 0.5 GB | 1.5 GB | Fits | Get file → | |
| Q3_K_M | 0.5 GB | 1.5 GB | Fits | Get file → | |
| Q3_K_L | 0.6 GB | 1.6 GB | Fits | Get file → | |
| IQ4_XS | 0.6 GB | 1.6 GB | Fits | Get file → | |
| Q4_0 | 0.6 GB | 1.6 GB | Fits | Get file → | |
| IQ4_NL | 0.6 GB | 1.6 GB | Fits | Get file → | |
| Q4_K_S | 0.6 GB | 1.6 GB | Fits | Get file → | |
| Q4_K_M | 0.7 GB | 1.6 GB | Fits | Get file → | |
| Q4_1 | 0.7 GB | 1.7 GB | Fits | Get file → | |
| Q5_K_S | 0.8 GB | 1.7 GB | Fits | Get file → | |
| Q5_K_M | 0.8 GB | 1.7 GB | Fits | Get file → | |
| Q6_K | 0.9 GB | 1.9 GB | Fits | Get file → |
For 8‑GB VRAM, use Q4_0 (0.64 GB, 1.6 GB memory at 8k context) or Q4_K_M (0.67 GB, 1.6 GB). For 4‑GB VRAM, choose IQ1_S (0.29 GB, 1.3 GB) or IQ1_M (0.31 GB, 1.3 GB). For 2‑GB VRAM, IQ2_XXS (0.34 GB, 1.3 GB) or IQ2_XS (0.36 GB, 1.3 GB) are suitable. Estimates are approximate.
What GPU do you need for K2 Horizon 0.9B 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 Q6_K (0.9 GB file, about 1.9 GB in use).
Which K2 Horizon 0.9B Heretic quant should you choose?
Q4_K_M is the usual starting point for K2 Horizon 0.9B Heretic: it balances file size and quality well. Here it is a 0.7 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
Source
Frequently asked questions about K2 Horizon 0.9B Heretic
How much VRAM does K2 Horizon 0.9B Heretic need?
About 1.6 GB at Q4_K_M with an 8K context window. That is the 0.7 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 0.9B Heretic on an 8 GB GPU?
Yes, with Q6_K: the 0.9 GB file needs about 1.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of K2 Horizon 0.9B Heretic GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 0.3 GB, IQ1_M is 0.3 GB, IQ2_XXS is 0.3 GB, IQ2_XS is 0.4 GB, IQ2_S is 0.4 GB and 19 more.
What context length does K2 Horizon 0.9B Heretic support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.
Where can I download K2 Horizon 0.9B Heretic GGUF?
The files are on Hugging Face in the mradermacher/K2-Horizon-0.9B-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 0.9B 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 0.9B Heretic on 8 GB VRAM?
Yes, a Q4_0 or Q4_K_M quant fits 8 GB VRAM with about 1.6 GB memory usage at 8k context.
Does this model support image input?
No, the model has no vision capability.
What license applies to this model?
The model is released under Apache‑2.0, inherited from the base checkpoint.