Mistral-Nemo-2407-12B-Thinking-Claude-Gemini-GPT5.2-Uncensored-HERETIC
12BMistralheretic
from mistralai/Mistral-Nemo-Instruct-2407
↓ 20.9K♥ 6213 repos
Mistral-Medium-3.5-128B-Eschaton-Uncensored
Mistral-Medium-3.5-128B-Eschaton-Uncensored is a abliterated and uncensored variant of mistralai/Mistral-Medium-3.5-128B, published on Hugging Face by cloudbjorn. It is 128B parameters, server-class deployment class and other licence. It is distributed across 5 repositories in Transformers, GGUF and GGUF (imatrix) formats, totalling 7.1K downloads.
Specification
- Model name
- Mistral-Medium-3.5-128B-Eschaton-Uncensored
- Source repository
- cloudbjorn/Mistral-Medium-3.5-128B-Eschaton-Uncensored
- Base model
- mistralai/Mistral-Medium-3.5-128B
- Publisher
- cloudbjorn
- Parameters
- 128B
- Hardware class
- 100B+ — server-class deployment
- Licence
- other
- Task
- Image text to text
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- Transformers, GGUF, GGUF (imatrix)
- First indexed
- 24 Jul 2026
- Last updated
- 26 Jul 2026
Ablation technique
How Mistral-Medium-3.5-128B-Eschaton-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
“This is a merged BF16 fine-tune of Mistral Medium 3.5 128B. Training loaded the full-BF16 axolotl-ai-co/Mistral-Medium-3.5-128B-BF16 checkpoint and used cloudbjorn/eschaton-uncensored with the Eschaton Engine.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download mradermacher/Mistral-Medium-3.5-128B-Eschaton-Uncensored-GGUF --local-dir ./mistral-medium-3.5-128b-eschaton-uncensored
llama-cli -m ./mistral-medium-3.5-128b-eschaton-uncensored/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "cloudbjorn/Mistral-Medium-3.5-128B-Eschaton-Uncensored"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve cloudbjorn/Mistral-Medium-3.5-128B-Eschaton-Uncensored --trust-remote-codeDownloads and variants (4)
Every published repository of Mistral-Medium-3.5-128B-Eschaton-Uncensored, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| mradermacher/Mistral-Medium-3.5-128B-Eschaton-Uncensored-GGUF | GGUF | 6K |
| mradermacher/Mistral-Medium-3.5-128B-Eschaton-Uncensored-i1-GGUF | GGUF (imatrix) | 1K |
| cloudbjorn/Mistral-Medium-3.5-128B-Eschaton-Uncensored-GGUF | GGUF | 96 |
| cloudbjorn/Mistral-Medium-3.5-128B-Eschaton-Uncensoredsource | Transformers | 17 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Mistral-Medium-3.5-128B-Eschaton-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 mistralai/Mistral-Medium-3.5-128B, not added by ablation — at 128B 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 other, but the terms that bind you are mistralai/Mistral-Medium-3.5-128B’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 Mistral-Medium-3.5-128B-Eschaton-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 cloudbjorn, and does not independently verify publisher claims. See responsible use.