Qwythos-9B-Claude-Mythos-5-1M
9BOtheruncensored
from empero-ai/Qwythos-9B-Claude-Mythos-5-1M
↓ 593K♥ 2.7K98 repos
Qwythos-9B-v2
Qwythos-9B-v2 is a abliterated and uncensored variant of empero-ai/Qwythos-9B-v2, published on Hugging Face by empero-ai. It is 9B parameters, single consumer GPU class and apache-2.0 licence. It is distributed across 12 repositories in GGUF, Transformers, MLX and GGUF (imatrix) formats, totalling 639.9K downloads.
Specification
- Model name
- Qwythos-9B-v2
- Source repository
- empero-ai/Qwythos-9B-v2
- Base model
- empero-ai/Qwythos-9B-v2
- Publisher
- empero-ai
- Parameters
- 9B
- 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, Transformers, MLX, GGUF (imatrix)
- First indexed
- 9 Jul 2026
- Last updated
- 24 Aug 2026
Ablation technique
How Qwythos-9B-v2 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
“The next iteration of Qwythos: all the reasoning of Qwythos-9B, with the looping behavior fixed. v2 keeps the deep chain-of-thought, the uncensored research posture, and the 1M-token context of its predecessor, and cleans up the rough edges that showed up in real use.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download empero-ai/Qwythos-9B-v2-GGUF --local-dir ./qwythos-9b-v2
llama-cli -m ./qwythos-9b-v2/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "empero-ai/Qwythos-9B-v2"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve empero-ai/Qwythos-9B-v2 --trust-remote-codeDownloads and variants (11)
Every published repository of Qwythos-9B-v2, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| empero-ai/Qwythos-9B-v2-GGUF | GGUF | 632.9K |
| empero-ai/Qwythos-9B-v2source | Transformers | 4K |
| mradermacher/Qwythos-9B-v2-i1-GGUF | GGUF (imatrix) | 1.1K |
| mradermacher/Qwythos-9B-v2-GGUF | GGUF | 608 |
| luxuansang/Qwythos-9B-v2-GGUF | GGUF | 280 |
| luxuansang/Qwythos-9B-v2 | Transformers | 269 |
| Fastiraz/Qwythos-9B-v2-GGUF | GGUF | 266 |
| IKN03/Qwythos-9B-v2-GGUF | GGUF | 186 |
| DarkKitsune/Qwythos-9B-v2-Q5_K_L-imat-GGUF | GGUF | 126 |
| Dzluck/Qwythos-9B-v2-GGUF | GGUF | 77 |
| JameslineUK/Qwythos-9B-v2-mlx-4Bit | MLX | 41 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Qwythos-9B-v2 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 empero-ai/Qwythos-9B-v2, 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 empero-ai/Qwythos-9B-v2’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 Qwythos-9B-v2 is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with empero-ai, and does not independently verify publisher claims. See responsible use.