⌦abliteratedmodels.org

MiniCPM-V-4.7-35B-A3B-Uncensored

MiniCPM-V-4.7-35B-A3B-Uncensored is a abliterated and uncensored variant of openbmb/MiniCPM-V-4.7-35B-A3B, published on Hugging Face by AtomicChat. It is 35B total parameters (mixture-of-experts), 48GB VRAM class class and apache-2.0 licence. It is distributed across 2 repositories in GGUF format, totalling 238.9K downloads.

Abliteration + uncensored fine-tune35B MoEMiniCPM25B – 50B↓ 238,860♥ 46
View on Hugging Face ↗Base model ↗

Specification

Model name
MiniCPM-V-4.7-35B-A3B-Uncensored
Source repository
AtomicChat/MiniCPM-V-4.7-35B-A3B-Uncensored-GGUF
Base model
openbmb/MiniCPM-V-4.7-35B-A3B
Publisher
AtomicChat
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
apache-2.0
Task
Image text to text
Context window
Not documented
Ablation scope
Not stated by the publisher
Formats available
GGUF
First indexed
12 Oct 2026
Last updated
28 Oct 2026

Ablation technique

How MiniCPM-V-4.7-35B-A3B-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

“One refusal direction projected out of OpenBMB's original weights, shipped two ways: three baked GGUF builds, and a 106 MB LoRA adapter for the MiniCPM-V 4.7 quants you already have. The measurements behind this card are public.”

Running it

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

llama.cpp / GGUF
hf download AtomicChat/MiniCPM-V-4.7-35B-A3B-Uncensored-GGUF --local-dir ./minicpm-v-4.7-35b-a3b-uncensored
llama-cli -m ./minicpm-v-4.7-35b-a3b-uncensored/<file>.gguf -p "..."
Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "AtomicChat/MiniCPM-V-4.7-35B-A3B-Uncensored-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
    repo, torch_dtype="auto", device_map="auto"
)
vLLM
vllm serve AtomicChat/MiniCPM-V-4.7-35B-A3B-Uncensored-GGUF --trust-remote-code

Downloads and variants (1)

The only published repository of MiniCPM-V-4.7-35B-A3B-Uncensored.

RepositoryFormatDownloads
AtomicChat/MiniCPM-V-4.7-35B-A3B-Uncensored-GGUFsourceGGUF238.9K

Security-team assessment

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

  • MiniCPM-V-4.7-35B-A3B-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 openbmb/MiniCPM-V-4.7-35B-A3B, 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 openbmb/MiniCPM-V-4.7-35B-A3B’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 MiniCPM-V-4.7-35B-A3B-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 AtomicChat, and does not independently verify publisher claims. See responsible use.