Cyber-Tiel-Coder-35B-A3B
35BOtheruncensored
from huihui-ai/Huihui-Ornith-1.5-35B-A3B-abliterated
↓ 1M♥ 3433 repos
Hermes-4-70B-heretic
Hermes-4-70B-heretic is a Heretic-ablated variant of meta-llama/Llama-3.1-70B, published on Hugging Face by hrktos-37. It is 70B parameters, multi-GPU class and llama3 licence. It is distributed across 4 repositories in Transformers, GGUF and GGUF (imatrix) formats, totalling 7.2K downloads.
Specification
- Model name
- Hermes-4-70B-heretic
- Source repository
- hrktos-37/Hermes-4-70B-heretic
- Base model
- meta-llama/Llama-3.1-70B
- Publisher
- hrktos-37
- Parameters
- 70B
- VRAM required
- ~43.3 GB at Q4_K_M, 4k context (estimated) — runs on 48 GB cards
- Hardware class
- 50B – 100B — multi-GPU
- Licence
- llama3
- Task
- Text generation
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- Transformers, GGUF, GGUF (imatrix)
- First indexed
- 2 Jan 2026
- Last updated
- 23 Oct 2026
Ablation technique
How Hermes-4-70B-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
“Hermes 4 70B is a frontier, hybrid-mode reasoning model based on Llama-3.1-70B by Nous Research that is aligned to you.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download mradermacher/Hermes-4-70B-heretic-GGUF --local-dir ./hermes-4-70b-heretic
llama-cli -m ./hermes-4-70b-heretic/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "hrktos-37/Hermes-4-70B-heretic"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve hrktos-37/Hermes-4-70B-heretic --trust-remote-codeDownloads and variants (3)
Every published repository of Hermes-4-70B-heretic, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| mradermacher/Hermes-4-70B-heretic-GGUF | GGUF | 6.5K |
| mradermacher/Hermes-4-70B-heretic-i1-GGUF | GGUF (imatrix) | 576 |
| hrktos-37/Hermes-4-70B-hereticsource | Transformers | 117 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Hermes-4-70B-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 meta-llama/Llama-3.1-70B, not added by ablation — at 70B 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.
- Declared licence is llama3, but the terms that bind you are meta-llama/Llama-3.1-70B’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 Hermes-4-70B-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 hrktos-37, and does not independently verify publisher claims. See responsible use.