⌦abliteratedmodels.org

Cyber-Tiel-Coder-35B-A3B-MTP-TTQ

Cyber-Tiel-Coder-35B-A3B-MTP-TTQ is a abliterated and uncensored variant of peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP, published on Hugging Face by TokenTinkerer. It is 35B total parameters (mixture-of-experts), 48GB VRAM class class and mit licence. It is distributed across 2 repositories in GGUF format, totalling 6.2K downloads.

Abliteration + uncensored fine-tune35B MoEOther25B – 50B↓ 6,157♥ 1
View on Hugging Face ↗Base model ↗

Specification

Model name
Cyber-Tiel-Coder-35B-A3B-MTP-TTQ
Source repository
TokenTinkerer/Cyber-Tiel-Coder-35B-A3B-MTP-TTQ-GGUF
Base model
peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP
Publisher
TokenTinkerer
Parameters
35B (mixture-of-experts)
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
mit
Task
Text generation
Context window
Not documented
Ablation scope
Not stated by the publisher
Formats available
GGUF
First indexed
25 Oct 2026
Last updated
2 Nov 2026

Ablation technique

How Cyber-Tiel-Coder-35B-A3B-MTP-TTQ 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

“TTQ (TokenTinkerer Quant) is a ten-rung GGUF ladder built from peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP, from 3.34 bpw to 6.64 bpw. Every rung is tensor-for-tensor the same shape as our published Qwen3.6-35B-A3B TTQ ladder — the same ten ftypes in the same places on 733 body tensors — with the model's...”

Running it

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

llama.cpp / GGUF
hf download TokenTinkerer/Cyber-Tiel-Coder-35B-A3B-MTP-TTQ-GGUF --local-dir ./cyber-tiel-coder-35b-a3b-mtp-ttq
llama-cli -m ./cyber-tiel-coder-35b-a3b-mtp-ttq/<file>.gguf -p "..."
Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "TokenTinkerer/Cyber-Tiel-Coder-35B-A3B-MTP-TTQ-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
    repo, torch_dtype="auto", device_map="auto"
)
vLLM
vllm serve TokenTinkerer/Cyber-Tiel-Coder-35B-A3B-MTP-TTQ-GGUF --trust-remote-code

Downloads and variants (1)

The only published repository of Cyber-Tiel-Coder-35B-A3B-MTP-TTQ.

RepositoryFormatDownloads
TokenTinkerer/Cyber-Tiel-Coder-35B-A3B-MTP-TTQ-GGUFsourceGGUF6.2K

Security-team assessment

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

  • Cyber-Tiel-Coder-35B-A3B-MTP-TTQ 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 peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP, 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 mit, but the terms that bind you are peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP’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 Cyber-Tiel-Coder-35B-A3B-MTP-TTQ is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with TokenTinkerer, and does not independently verify publisher claims. See responsible use.