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

Libraries

How to use ansulev/Mythos-nano-gguf-free with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ansulev/Mythos-nano-gguf-free")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ansulev/Mythos-nano-gguf-free")
model = AutoModelForCausalLM.from_pretrained("ansulev/Mythos-nano-gguf-free")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ansulev/Mythos-nano-gguf-free with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ansulev/Mythos-nano-gguf-free

SGLang

How to use ansulev/Mythos-nano-gguf-free with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ansulev/Mythos-nano-gguf-free" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ansulev/Mythos-nano-gguf-free",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ansulev/Mythos-nano-gguf-free" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ansulev/Mythos-nano-gguf-free",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ansulev/Mythos-nano-gguf-free with Docker Model Runner:
```
docker model run hf.co/ansulev/Mythos-nano-gguf-free
```

I, (me), just removed the gguf's for those who dont want to download 40GB of model weighs, so now you have the safetensors now for easier use and fine tuning.

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

Mythos-nano

🚨 This model was not trained on tool-calling or agent-based programming data. We therefore do not recommend using it for tasks that involve function calling, API orchestration, or autonomous coding agents. For programming tasks, we recommend using this model on competitive programming problems (e.g., LeetCode-style) - Weibo Lab.

⚠️ Abliterated (uncensored): the refusal direction has been removed, so this model will not decline requests a safety-tuned model normally would. Safety guardrails are reduced — use responsibly and at your own risk; you are solely responsible for outputs and legal compliance.

🏆 Benchmarks

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("FlameF0X/Mythos-nano-safetensors-only")
model = AutoModelForCausalLM.from_pretrained("FlameF0X/Mythos-nano-safetensors-only", 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))