⌦abliteratedmodels.org

Apex-35B-V1.0-Uncensored-Sangreal-ICE

Apex-35B-V1.0-Uncensored-Sangreal-ICE is a abliterated and uncensored variant of Apexintelligence-AI/Apex-35B-V1.0, published on Hugging Face by gbuzhf. It is 35B parameters, 48GB VRAM class class and apache-2.0 licence. It is distributed across 2 repositories in GGUF format, totalling 6.2K downloads.

Abliteration + uncensored fine-tune35BOther25B – 50B↓ 6,153♥ 2
View on Hugging Face ↗Base model ↗

Specification

Model name
Apex-35B-V1.0-Uncensored-Sangreal-ICE
Source repository
gbuzhf/Apex-35B-V1.0-Uncensored-Sangreal-ICE
Base model
Apexintelligence-AI/Apex-35B-V1.0
Publisher
gbuzhf
Parameters
35B
VRAM required
~22.1 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
Image text to text
Context window
Not documented
Ablation scope
Not stated by the publisher
Formats available
GGUF
First indexed
29 Oct 2026
Last updated
30 Oct 2026

Ablation technique

How Apex-35B-V1.0-Uncensored-Sangreal-ICE 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

“refusal direction removed, made with a Sangreal 10k importance matrix, ICE 1.6 per-tensor recipes and ICE 2.0 post-quantization expert repair. Every file keeps the MTP draft layer; the vision projector ships separately (F16, plus a Q80). Every file carries the Arrow 4.0-apex chat template.”

Running it

Commands are templates — confirm the exact repository and quant file before use.

llama.cpp / GGUF
hf download gbuzhf/Apex-35B-V1.0-Uncensored-Sangreal-ICE --local-dir ./apex-35b-v1.0-uncensored-sangreal-ice
llama-cli -m ./apex-35b-v1.0-uncensored-sangreal-ice/<file>.gguf -p "..."
Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "gbuzhf/Apex-35B-V1.0-Uncensored-Sangreal-ICE"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
    repo, torch_dtype="auto", device_map="auto"
)
vLLM
vllm serve gbuzhf/Apex-35B-V1.0-Uncensored-Sangreal-ICE --trust-remote-code

Downloads and variants (1)

The only published repository of Apex-35B-V1.0-Uncensored-Sangreal-ICE.

RepositoryFormatDownloads
gbuzhf/Apex-35B-V1.0-Uncensored-Sangreal-ICEsourceGGUF6.2K

Security-team assessment

Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.

  • Apex-35B-V1.0-Uncensored-Sangreal-ICE 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 Apexintelligence-AI/Apex-35B-V1.0, not added by ablation — at 35B 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 Apexintelligence-AI/Apex-35B-V1.0’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 Apex-35B-V1.0-Uncensored-Sangreal-ICE is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with gbuzhf, and does not independently verify publisher claims. See responsible use.