Spark-x2.5-4B-Heretic-jp
4BOtherheretic
from XHToken/Spark-X2.5-4B
↓ 452.1K♥ 182 repos
LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3
LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3 is a refusal-ablated variant of DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3, published on Hugging Face by DuoNeural. It is 8B total parameters (mixture-of-experts), single consumer GPU class and other licence. It is distributed across 8 repositories in GGUF, Transformers, GGUF (imatrix) and MLX formats, totalling 13.5K downloads.
Specification
- Model name
- LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3
- Source repository
- DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3
- Publisher
- DuoNeural
- Parameters
- 8B (mixture-of-experts)
- VRAM required
- ~5.6 GB at Q4_K_M, 4k context (estimated) — runs on 6 GB cards
- Hardware class
- 4B – 10B — single consumer GPU
- Licence
- other
- Task
- Text generation
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF, Transformers, GGUF (imatrix), MLX
- First indexed
- 18 Sept 2026
- Last updated
- 9 Oct 2026
Ablation technique
How LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3 was modified, and what that implies.
Abliteration (directional ablation)
The single residual-stream direction that mediates refusal is identified from harmful/harmless prompt pairs and projected out of the model weights.
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
“DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3 is the latest, apex-tier autonomous agentic coding model trained by DuoNeural (Aura ✨, Archon, and Jesse).”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3-GGUF --local-dir ./lfm2.5-8b-a1b-hermes-agentic-coder-abliterated-v3
llama-cli -m ./lfm2.5-8b-a1b-hermes-agentic-coder-abliterated-v3/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3 --trust-remote-codeDownloads and variants (7)
Every published repository of LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3, including quantised re-releases by other authors.
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3 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 DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3, not added by ablation — at 8B parameters, expect a small model’s reasoning and a high error rate on exploit detail.
- The publisher does not state which layers were ablated, so assume nothing about refusal consistency — probe it directly.
- Declared licence is other, but the terms that bind you are DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3’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 LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3 is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with DuoNeural, and does not independently verify publisher claims. See responsible use.