Spark-x2.5-4B-Heretic-jp
4BOtherheretic
from XHToken/Spark-X2.5-4B
↓ 452.1K♥ 182 repos
Mythos-V2-9B
Mythos-V2-9B is a abliterated and uncensored variant of fableforge-ai/Mythos-V2-9B, published on Hugging Face by fableforge-ai. It is 9B parameters, single consumer GPU class and apache-2.0 licence. It is distributed across 3 repositories in GGUF format, totalling 8.8K downloads.
Specification
- Model name
- Mythos-V2-9B
- Source repository
- fableforge-ai/Mythos-V2-9B-GGUF
- Base model
- fableforge-ai/Mythos-V2-9B
- Publisher
- fableforge-ai
- 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
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF
- First indexed
- 8 Jul 2026
- Last updated
- 21 Oct 2026
Ablation technique
How Mythos-V2-9B 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
“Not sure? Take Q4KM. Low RAM → IQ4XS. Max quality → Q6K.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
Ollama (publisher-documented)
ollama run fableforge-ai/mythos-v2-9bllama.cpp / GGUF
hf download fableforge-ai/Mythos-V2-9B-GGUF --local-dir ./mythos-v2-9b
llama-cli -m ./mythos-v2-9b/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "fableforge-ai/Mythos-V2-9B-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve fableforge-ai/Mythos-V2-9B-GGUF --trust-remote-codeDownloads and variants (2)
Every published repository of Mythos-V2-9B, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| fableforge-ai/Mythos-V2-9B-GGUFsource | GGUF | 8.4K |
| fableforge-ai/Mythos-V2-9B | GGUF | 408 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Mythos-V2-9B 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 fableforge-ai/Mythos-V2-9B, 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 fableforge-ai/Mythos-V2-9B’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 Mythos-V2-9B is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with fableforge-ai, and does not independently verify publisher claims. See responsible use.