Spark-x2.5-4B-Heretic-jp
4BOtherheretic
from XHToken/Spark-X2.5-4B
↓ 452.1K♥ 182 repos
NeoHorse-1-9B-Uncensored-GSQ-RCO
NeoHorse-1-9B-Uncensored-GSQ-RCO is a abliterated and uncensored variant of TokenRhythm/NeoHorse-1-9B, published on Hugging Face by abenzerps. It is 9B parameters, single consumer GPU class and apache-2.0 licence. It is distributed across 2 repositories in GGUF format, totalling 6.8K downloads.
Specification
- Model name
- NeoHorse-1-9B-Uncensored-GSQ-RCO
- Source repository
- abenzerps/NeoHorse-1-9B-Uncensored-GSQ-RCO-GGUF
- Base model
- TokenRhythm/NeoHorse-1-9B
- Publisher
- abenzerps
- Parameters
- 9B
- VRAM required
- ~6.2 GB at Q4_K_M, 4k context (estimated) — runs on 8 GB cards
- Hardware class
- 4B – 10B — single consumer GPU
- Licence
- apache-2.0
- Task
- Text generation
- Context window
- 131K tokens (as documented)
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF
- First indexed
- 23 Oct 2026
- Last updated
- 25 Oct 2026
Ablation technique
How NeoHorse-1-9B-Uncensored-GSQ-RCO 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
“Mixed-precision GSQ-RCO GGUF quantizations of TokenRhythm/NeoHorse-1-9B, optimized for efficient, high-fidelity local inference in llama.cpp. The model supports a context length of up to 262,144 tokens (262K).”
Running it
Commands are templates — confirm the exact repository and quant file before use.
Ollama (publisher-documented)
ollama run hf.co/abenzerps/NeoHorse-1-9B-Uncensored-GSQ-RCO-GGUF:IQ3_Mllama.cpp / GGUF
hf download abenzerps/NeoHorse-1-9B-Uncensored-GSQ-RCO-GGUF --local-dir ./neohorse-1-9b-uncensored-gsq-rco
llama-cli -m ./neohorse-1-9b-uncensored-gsq-rco/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "abenzerps/NeoHorse-1-9B-Uncensored-GSQ-RCO-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve abenzerps/NeoHorse-1-9B-Uncensored-GSQ-RCO-GGUF --trust-remote-codeDownloads and variants (1)
The only published repository of NeoHorse-1-9B-Uncensored-GSQ-RCO.
| Repository | Format | Downloads |
|---|---|---|
| abenzerps/NeoHorse-1-9B-Uncensored-GSQ-RCO-GGUFsource | GGUF | 6.8K |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- NeoHorse-1-9B-Uncensored-GSQ-RCO 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 TokenRhythm/NeoHorse-1-9B, not added by ablation — at 9B 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.
- 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 TokenRhythm/NeoHorse-1-9B’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 NeoHorse-1-9B-Uncensored-GSQ-RCO is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with abenzerps, and does not independently verify publisher claims. See responsible use.