Instructions to use squ11z1/Mythos-nano with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use squ11z1/Mythos-nano with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="squ11z1/Mythos-nano",
	filename="mythos-nano-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use squ11z1/Mythos-nano with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf squ11z1/Mythos-nano:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf squ11z1/Mythos-nano:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf squ11z1/Mythos-nano:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf squ11z1/Mythos-nano:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf squ11z1/Mythos-nano:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf squ11z1/Mythos-nano:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf squ11z1/Mythos-nano:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf squ11z1/Mythos-nano:Q4_K_M

Use Docker

docker model run hf.co/squ11z1/Mythos-nano:Q4_K_M

LM Studio
Jan

vLLM

How to use squ11z1/Mythos-nano with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "squ11z1/Mythos-nano"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "squ11z1/Mythos-nano",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/squ11z1/Mythos-nano:Q4_K_M

Ollama
How to use squ11z1/Mythos-nano with Ollama:
```
ollama run hf.co/squ11z1/Mythos-nano:Q4_K_M
```

Unsloth Studio

How to use squ11z1/Mythos-nano with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for squ11z1/Mythos-nano to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for squ11z1/Mythos-nano to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for squ11z1/Mythos-nano to start chatting

How to use squ11z1/Mythos-nano with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf squ11z1/Mythos-nano:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "squ11z1/Mythos-nano:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use squ11z1/Mythos-nano with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf squ11z1/Mythos-nano:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default squ11z1/Mythos-nano:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use squ11z1/Mythos-nano with Docker Model Runner:
```
docker model run hf.co/squ11z1/Mythos-nano:Q4_K_M
```

Lemonade

How to use squ11z1/Mythos-nano with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull squ11z1/Mythos-nano:Q4_K_M

Run and chat with the model

lemonade run user.Mythos-nano-Q4_K_M

List all available models

lemonade list

Disclaimer: This is not an official release by Anthropic.
Mythos-nano is an independent open model project.

Mythos-nano

🏆 Benchmarks

Mythos-nano (3B) vs. frontier models. +CLR = with test-time CLR boost.

Benchmark	Mythos-nano	+CLR	Qwen3.6 Plus	Gemini 3 Pro	GLM-5	Kimi K2.5	Claude Opus 4.5
AIME'25	91.4	96.7	93.3	96.0	96.7	96.1	92.8
AIME'26	94.3	97.1	95.3	91.7	95.8	93.3	95.1
HMMT'25	89.3	95.4	96.7	97.5	97.9	95.4	92.9
IMO-AnswerBench	76.4	80.6	83.8	83.1	82.5	81.8	78.5
LiveCodeBench v6	80.2	—	87.1	87.4	85.5	85.0	84.8
IFBench	74.5	—	74.2	70.4	76.5	70.0	58.0

Full comparison (mathematics · coding · knowledge · instruction)

Model	Params	AIME25	AIME26	HMMT25	BruMO25	IMO-Ans	LCBv6	OJBench	GPQA-D	IFEval	IFBench
Kimi K2.5	1T	96.1	93.3	95.4	98.3	81.8	85.0	54.7	87.6	93.9	70.0
GLM-5	744B	96.7	95.8	97.9	–	82.5	85.5	55.0	86.0	92.6	76.5
DeepSeek V3.2	671B	93.1	94.2	90.2	96.7	78.3	80.8	48.4	82.4	92.6	60.7
Gemini 3 Pro	N/A	96.0	91.7	97.5	98.3	83.1	87.4	58.8	91.9	–	70.4
Claude Opus 4.5	N/A	92.8	95.1	92.9	–	78.5	84.8	–	87.0	–	58.0
GPT-5 (high)	N/A	94.6	–	88.3	91.7	76.0	84.5	–	85.7	–	73.1
Mythos-nano	3B	91.4	94.3	89.3	93.8	76.4	80.2	38.6	70.2	93.4	74.5
Mythos-nano + CLR	3B	96.7	97.1	95.4	99.2	80.6	–	–	72.9	–	–

LeetCode contests (Python, pass-rate)

Model	Aggregate
GPT-5.3-Codex	100.0% (128/128)
Gemini 3.1 Pro	99.2% (127/128)
Gemini 3 Flash	96.9% (124/128)
Mythos-nano	96.1% (123/128)
GPT-5.2	95.3% (122/128)
Qwen3-Max	91.4% (117/128)
Kimi K2.5	90.6% (116/128)
Claude Opus 4.6	86.7% (111/128)

A 3B model placing within ~4 points of trillion-parameter systems on competition math and live code — the core thesis: with verifiable feedback, small models reach frontier reasoning.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
tok = AutoTokenizer.from_pretrained("squ11z1/Mythos-nano")
model = AutoModelForCausalLM.from_pretrained("squ11z1/Mythos-nano", dtype=torch.bfloat16, device_map="cuda")
msgs = [{"role": "user", "content": "Find all integer solutions of x^2 - y^2 = 12."}]
ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt").to("cuda")
print(tok.decode(model.generate(ids, max_new_tokens=2048, temperature=0.6)[0], skip_special_tokens=True))