Cyber-Tiel-Coder-35B-A3B
35BOtheruncensored
from huihui-ai/Huihui-Ornith-1.5-35B-A3B-abliterated
↓ 1M♥ 3433 repos
Artemis-31B-v1.2-heretic
Artemis-31B-v1.2-heretic is a Heretic-ablated variant of TheDrummer/Artemis-31B-v1.2, published on Hugging Face by sjorsb. It is 31B parameters and 48GB VRAM class class. It is distributed across 4 repositories in GGUF (imatrix), Transformers and GGUF formats, totalling 9.2K downloads.
Specification
- Model name
- Artemis-31B-v1.2-heretic
- Source repository
- sjorsb/Artemis-31B-v1.2-heretic
- Base model
- TheDrummer/Artemis-31B-v1.2
- Publisher
- sjorsb
- Parameters
- 31B
- VRAM required
- ~19.7 GB at Q4_K_M, 4k context (estimated) — runs on 24 GB cards
- Hardware class
- 25B – 50B — 48GB VRAM class
- Licence
- Not declared
- Task
- Unspecified
- Context window
- 20K tokens (as documented)
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF (imatrix), Transformers, GGUF
- First indexed
- 23 Oct 2026
- Last updated
- 31 Oct 2026
Ablation technique
How Artemis-31B-v1.2-heretic was modified, and what that implies.
Heretic
Automated directional ablation via the Heretic toolchain, which searches for the refusal direction and applies it with a KL-divergence budget so general capability is preserved.
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
“Artemis v1.2 landed as the strongest Artemis yet — and, for several testers, the strongest Gemma 4 tune they've used. The recurring themes:”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download mradermacher/Artemis-31B-v1.2-heretic-i1-GGUF --local-dir ./artemis-31b-v1.2-heretic
llama-cli -m ./artemis-31b-v1.2-heretic/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "sjorsb/Artemis-31B-v1.2-heretic"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve sjorsb/Artemis-31B-v1.2-heretic --trust-remote-codeDownloads and variants (3)
Every published repository of Artemis-31B-v1.2-heretic, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| mradermacher/Artemis-31B-v1.2-heretic-i1-GGUF | GGUF (imatrix) | 7.4K |
| mradermacher/Artemis-31B-v1.2-heretic-GGUF | GGUF | 1.8K |
| sjorsb/Artemis-31B-v1.2-hereticsource | Transformers | 53 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Artemis-31B-v1.2-heretic 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 TheDrummer/Artemis-31B-v1.2, not added by ablation — at 31B 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.
- No licence is declared on this repository, which is a compliance problem in itself. Resolve it against the base model’s terms before use.
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 Artemis-31B-v1.2-heretic is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with sjorsb, and does not independently verify publisher claims. See responsible use.