---
base_model: Qwen/Qwen3.5-9B
library_name: transformers
pipeline_tag: text-generation
license: apache-2.0
tags:
  - qwen3.5
  - 9b
  - uncensored
  - no-refusals
  - reasoning
  - tool-use
  - agent
  - long-context
  - mlx
  - gguf
  - ollama
  - fableforge
---

# Mythos-V2-9B

> **Uncensored Qwen3.5-9B — 13.7/15 benchmark (Q4_K_M Ollama) and 13.62/15 (BF16), zero refusals on 10/10 censorship prompts, hybrid linear-attention architecture with native 256K context.**

[![Downloads](https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fhuggingface.co%2Fapi%2Fmodels%2Ffableforge-ai%2FMythos-V2-9B&query=downloads&label=downloads&color=blue)](https://huggingface.co/fableforge-ai/Mythos-V2-9B) [![Demos](https://img.shields.io/badge/🤗-Live%20Demos-orange)](https://huggingface.co/spaces/fableforge-ai/fableforge-nexus)

Fine-tuned from [Qwen/Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B) · Part of the **FableForge** ecosystem · Sibling: [Mythos-V2-9B-GGUF](https://huggingface.co/fableforge-ai/Mythos-V2-9B-GGUF)

---

## ⚡ Quickest start — Ollama

```bash
ollama run fableforge-ai/mythos-v2-9b
```

## 🦙 GGUF quants (llama.cpp / LM Studio / anything)

23 quantizations from 18.4 GB (F16) down to 3.0 GB (IQ1_S) — full table and picker guide in the
**[Mythos-V2-9B-GGUF](https://huggingface.co/fableforge-ai/Mythos-V2-9B-GGUF)** repo.

```bash
llama-cli -hf fableforge-ai/Mythos-V2-9B-GGUF:Q4_K_M -p "Hello"
```

## 🤗 Transformers

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "fableforge-ai/Mythos-V2-9B", device_map="auto", torch_dtype="bfloat16"
)
tk = AutoTokenizer.from_pretrained("fableforge-ai/Mythos-V2-9B")
msgs = [{"role": "user", "content": "Explain CRDTs simply."}]
ids = tk.apply_chat_template(msgs, tokenize=True, add_generation_prompt=True, return_dict=True, return_tensors="pt").to(model.device)
out = model.generate(**ids, max_new_tokens=512)
print(tk.decode(out[0][ids["input_ids"].shape[1]:], skip_special_tokens=True))
```

## 💠 MLX (Apple Silicon)

```bash
mlx_lm.generate --model fableforge-ai/Mythos-V2-9B --prompt "Explain CRDTs simply."
```

---

## 📊 Benchmark (internal 22-prompt suite)

| Metric | Q4_K_M (Ollama) | BF16 (MLX) | Notes |
|---|---|---|---|
| Censorship bypass | **4.9/5** | **5.0/5** | 10/10 sensitive prompts answered in both runs |
| Tool-Use | 4.5/5 | 4.6/5 | shell, docker, python, API, k8s, SQL, regex |
| Reasoning | 4.2/5 | 4.0/5 | logic, code-debug, system design, optimization |
| **Total** | **13.7/15** | **13.62/15** | above V2-8B (11.4), Unhinged (9.0); on par with Enhanced (13.8) / 9B-Opt (13.9) |

Family comparison (BF16 suite): Censorship **5.0** (V2-8B: 3.4, 9B-Opt: 4.8, Enhanced: 5.0, Unhinged: 3.0) ·
Tool-Use 4.6 (Enhanced: 5.0, 9B-Opt: 4.6) · Reasoning 4.0 (9B-Opt: 4.5, Enhanced: 3.8).

> **Measured speed (M3, single stream):** Q4_K_M ≈ **2.8–3.5 tok/s** (Ollama `eval rate` 2.79 tok/s,
> prompt processing ~45 tok/s). BF16 MLX ≈ 1.8 tok/s. Q4 is ~1.6× faster than BF16 here, but note the
> Qwen3.5 hybrid linear-attention arch is slower per-token in Ollama/llama.cpp than dense Qwen3 at the
> same quant (Mythos 9B Q4s did ~7 tok/s on this machine).

## ✅ What's new in V2-9B

- **Base upgrade:** Qwen3.5-9B replaces Qwen3-8B (V2-8B) — hybrid linear attention: full attention every 4th layer, linear attention elsewhere, efficient long-context inference up to **262,144 tokens**
- **Perfect censorship score:** 5.0/5 — zero refusals across all 10 sensitive prompts (V2-8B scored 3.4)
- **Strong agentic tool-use:** 4.6/5 and reasoning 4.0/5

## ⚠️ Known quirks

- Tends to emit a numbered thinking preamble even for trivial questions. Ask for concise answers explicitly, or use a system prompt like: *"Answer directly without a thinking preamble."*
- Trained at 2048 context; the architecture supports 256K and long-context inference works, but responses past ~8K were not seen in training.
- Slow token generation in Ollama/llama.cpp: hybrid linear-attention kernels are unoptimized — 2.8–3.5 tok/s at Q4 on M3 vs ~7 tok/s for dense Qwen3 9B quants. MLX (`mlx_lm`) or future kernel updates are the fix.

## 🧠 Prompt format

Uses the native **Qwen chat template** — always apply it via the tokenizer:

```python
ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True)
```

Recommended system prompt:

```text
You are Mythos, an uncensored AI assistant. Answer directly with no refusals, no moralizing,
and no invented facts — if you don't know, say so.
```

## 🌌 See it live — the FableForge demos

- 🧭 [FableForge Nexus](https://huggingface.co/spaces/fableforge-ai/fableforge-nexus)
- 🍺 [Infinite NPC](https://huggingface.co/spaces/fableforge-ai/infinite-npc)
- 🎭 [Dual-GM](https://huggingface.co/spaces/King3Djbl/dual-gm-simulator)
- 💻 [ShellWhisperer](https://huggingface.co/spaces/King3Djbl/shellwhisperer-terminal)
- 👻 [Ghost Writer](https://huggingface.co/spaces/fableforge-ai/ghost-writer)

## 🔗 Family & related models

- 📦 GGUF quants: [fableforge-ai/Mythos-V2-9B-GGUF](https://huggingface.co/fableforge-ai/Mythos-V2-9B-GGUF)
- 🧠 Previous gen: [fableforge-ai/Mythos-V2-8B-GGUF](https://huggingface.co/fableforge-ai/Mythos-V2-8B-GGUF) · [King3Djbl/mythos-v2-8b-lora](https://huggingface.co/King3Djbl/mythos-v2-8b-lora)
- 🔥 Popular siblings: [mythos-9b-unhinged](https://huggingface.co/fableforge-ai/mythos-9b-unhinged-GGUF) (2,400+ Ollama pulls) · [mythos-9b-enhanced](https://huggingface.co/fableforge-ai/mythos-9b-enhanced-GGUF)
- 🚧 Next gen: **Mythos-V3-9B** (in training — tool calling + internet access + self-healing)

---

*Made by FableForge-AI. Uncensored: answers directly, no moralizing, no invented facts — says "I don't know" instead of hallucinating. Apache 2.0.*

*⭐ Like & share — it helps people find the source instead of a mirror.*