Cyber-Tiel-Coder-35B-A3B
35BOtheruncensored
from huihui-ai/Huihui-Ornith-1.5-35B-A3B-abliterated
↓ 1M♥ 3433 repos
K2-Horizon-MoVA-36B-A4B-uncensored
K2-Horizon-MoVA-36B-A4B-uncensored is a abliterated and uncensored variant of IFM/K2-Horizon-MoVA-36B-A4B, published on Hugging Face by InfinimindCreations. It is 36B total parameters (mixture-of-experts), 48GB VRAM class class and apache-2.0 licence. It is distributed across 5 repositories in Transformers, GGUF and GGUF (imatrix) formats, totalling 16.2K downloads.
Specification
- Model name
- K2-Horizon-MoVA-36B-A4B-uncensored
- Source repository
- InfinimindCreations/K2-Horizon-MoVA-36B-A4B-uncensored
- Base model
- IFM/K2-Horizon-MoVA-36B-A4B
- Publisher
- InfinimindCreations
- Parameters
- 36B (mixture-of-experts)
- VRAM required
- ~22.7 GB at Q4_K_M, 4k context (estimated) — runs on 24 GB cards
- Hardware class
- 25B – 50B — 48GB VRAM class
- Licence
- apache-2.0
- Task
- Text generation
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- Transformers, GGUF, GGUF (imatrix)
- First indexed
- 15 Sept 2026
- Last updated
- 15 Oct 2026
Ablation technique
How K2-Horizon-MoVA-36B-A4B-uncensored was modified, and what that implies.
Abliteration + uncensored fine-tune
Directional ablation combined with additional fine-tuning on unfiltered data, so behaviour diverges from the base model beyond refusal removal alone.
Reported scope: Not stated by the publisher. Publishers frequently omit this, so verify behaviour empirically rather than assuming full coverage.
From the publisher’s model card
“Uncensored version of IFM K2-Horizon-MoVA-36B-A4B, with refusal behavior removed through rank-3 directional ablation: three mutually independent refusal directions, the third measured under the ablation of the first two.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download mradermacher/K2-Horizon-MoVA-36B-A4B-uncensored-i1-GGUF --local-dir ./k2-horizon-mova-36b-a4b-uncensored
llama-cli -m ./k2-horizon-mova-36b-a4b-uncensored/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "InfinimindCreations/K2-Horizon-MoVA-36B-A4B-uncensored"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve InfinimindCreations/K2-Horizon-MoVA-36B-A4B-uncensored --trust-remote-codeDownloads and variants (4)
Every published repository of K2-Horizon-MoVA-36B-A4B-uncensored, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| mradermacher/K2-Horizon-MoVA-36B-A4B-uncensored-i1-GGUF | GGUF (imatrix) | 11.9K |
| mradermacher/K2-Horizon-MoVA-36B-A4B-uncensored-GGUF | GGUF | 3.4K |
| InfinimindCreations/K2-Horizon-MoVA-36B-A4B-uncensored-GGUF | GGUF | 708 |
| InfinimindCreations/K2-Horizon-MoVA-36B-A4B-uncensoredsource | Transformers | 193 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- K2-Horizon-MoVA-36B-A4B-uncensored will attempt offensive-security prompts that a hosted commercial model declines, which is what makes it usable for red-team corpus generation and for measuring what an unaligned model of this class produces.
- Capability is inherited from IFM/K2-Horizon-MoVA-36B-A4B, not added by ablation — at 36B parameters, expect roughly the base model’s competence, minus some instruction-following fidelity.
- The publisher does not state which layers were ablated, so assume nothing about refusal consistency — probe it directly.
- This release adds fine-tuning on unfiltered data, so its behaviour diverges from the base model beyond refusal removal — differences you measure cannot be attributed to ablation alone.
- Declared licence is apache-2.0, but the terms that bind you are IFM/K2-Horizon-MoVA-36B-A4B’s — a re-release cannot grant more than its parent.
Handling: run it isolated, put moderation in front of it if anyone outside your team can reach it, and verify the weights before loading — these are third-party artifacts. Full handling and licence guidance.
Metadata for K2-Horizon-MoVA-36B-A4B-uncensored is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with InfinimindCreations, and does not independently verify publisher claims. See responsible use.