Instructions to use VIDraft/Darwin-35B-A3B-Mythos with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use VIDraft/Darwin-35B-A3B-Mythos with Transformers:

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

pipe = pipeline("text-generation", model="VIDraft/Darwin-35B-A3B-Mythos")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("VIDraft/Darwin-35B-A3B-Mythos", device_map="auto")

llama-cpp-python

How to use VIDraft/Darwin-35B-A3B-Mythos with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="VIDraft/Darwin-35B-A3B-Mythos",
	filename="mythos-35b-IQ1_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 VIDraft/Darwin-35B-A3B-Mythos with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf VIDraft/Darwin-35B-A3B-Mythos:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf VIDraft/Darwin-35B-A3B-Mythos:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf VIDraft/Darwin-35B-A3B-Mythos:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf VIDraft/Darwin-35B-A3B-Mythos: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 VIDraft/Darwin-35B-A3B-Mythos:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf VIDraft/Darwin-35B-A3B-Mythos: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 VIDraft/Darwin-35B-A3B-Mythos:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf VIDraft/Darwin-35B-A3B-Mythos:Q4_K_M

Use Docker

docker model run hf.co/VIDraft/Darwin-35B-A3B-Mythos:Q4_K_M

LM Studio
Jan

vLLM

How to use VIDraft/Darwin-35B-A3B-Mythos with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "VIDraft/Darwin-35B-A3B-Mythos"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VIDraft/Darwin-35B-A3B-Mythos",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/VIDraft/Darwin-35B-A3B-Mythos:Q4_K_M

SGLang

How to use VIDraft/Darwin-35B-A3B-Mythos 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 "VIDraft/Darwin-35B-A3B-Mythos" \
    --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": "VIDraft/Darwin-35B-A3B-Mythos",
		"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 "VIDraft/Darwin-35B-A3B-Mythos" \
        --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": "VIDraft/Darwin-35B-A3B-Mythos",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use VIDraft/Darwin-35B-A3B-Mythos with Ollama:
```
ollama run hf.co/VIDraft/Darwin-35B-A3B-Mythos:Q4_K_M
```

Unsloth Studio

How to use VIDraft/Darwin-35B-A3B-Mythos 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 VIDraft/Darwin-35B-A3B-Mythos 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 VIDraft/Darwin-35B-A3B-Mythos to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for VIDraft/Darwin-35B-A3B-Mythos to start chatting

How to use VIDraft/Darwin-35B-A3B-Mythos with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf VIDraft/Darwin-35B-A3B-Mythos: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": "VIDraft/Darwin-35B-A3B-Mythos:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use VIDraft/Darwin-35B-A3B-Mythos with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf VIDraft/Darwin-35B-A3B-Mythos: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 VIDraft/Darwin-35B-A3B-Mythos:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use VIDraft/Darwin-35B-A3B-Mythos with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf VIDraft/Darwin-35B-A3B-Mythos:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "VIDraft/Darwin-35B-A3B-Mythos:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use VIDraft/Darwin-35B-A3B-Mythos with Docker Model Runner:
```
docker model run hf.co/VIDraft/Darwin-35B-A3B-Mythos:Q4_K_M
```

Lemonade

How to use VIDraft/Darwin-35B-A3B-Mythos with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull VIDraft/Darwin-35B-A3B-Mythos:Q4_K_M

Run and chat with the model

lemonade run user.Darwin-35B-A3B-Mythos-Q4_K_M

List all available models

lemonade list

Darwin-35B-A3B-Mythos

A measured Qwen3.6-35B-A3B reasoning derivative — frontier-class quality with published benchmarks, Korean capability, and a real on-device story. By VIDRAFT.

Most 35B-A3B derivatives on the hub ship a quant with no numbers. Darwin-35B-A3B-Mythos leads with measured results and stays fully reproducible under Apache-2.0.

Highlights (all measured, labeled)

Metric	Value	Method
GPQA Diamond	86.4	maj@8
GPQA Diamond	70.7	greedy (single-pass)
On-device decode (VKUE)	20.0 tok/s	RTX 5060 Laptop 8GB, Q3_K_M, measured
vs dense 32B on same laptop	3.7× faster	measured A/B (dense 32B = 5.36 tok/s)
Datacenter throughput (VKAE)	18,057 tok/s aggregate	1× B200, measured

34.7B total / ~3B active (A3B sparse MoE) — decode cost scales with the 3 active billion, so it is fast on small hardware.
Korean-capable — no Korean-specialist model exists in the current trending set; Mythos speaks it.
Apache-2.0, reproducible, honestly benchmarked.

Files

File	Quant	Size	Fits
`mythos-35b-Q4_K_M.gguf`	Q4_K_M	21.2 GB	24GB GPU / 32GB RAM
`mythos-35b-Q3_K_M.gguf`	Q3_K_M	16.8 GB	24GB card / laptop
`mythos-35b-Q2_K.gguf`	Q2_K	12.9 GB	16GB
`mythos-35b-IQ1_M.gguf`	IQ1_M (imatrix)	8.2 GB	12GB / edge

Coming: MTP-GGUF (native multi-token-prediction head, for self-speculative decode), NVFP4, FP8.

Run (llama.cpp)

Needs a recent llama.cpp build with qwen35moe support. Optimal on an 8GB card = experts on CPU, attention on GPU:

llama-cli -m mythos-35b-Q3_K_M.gguf -ngl 99 --n-cpu-moe 99 -c 8192 -p "..."

What's in v1 vs roadmap (honest)

v1 (this release): the measured Qwen3.6-35B-A3B derivative above — GPQA 86.4/70.7, Korean, full GGUF ladder, VKUE on-device numbers. Text-only (the vision tower is not included in this build).

Roadmap (not in v1 — will be labeled when shipped): DELPHI test-time reasoning layer (token-efficient thinking), native function-calling SFT, extended context, restored vision (mmproj), MTP-GGUF / NVFP4 format parity, and a live demo Space. We ship numbers when they are measured, not before.

Engines

VKUE (ubiquity): the same weights run from a datacenter GPU down to an 8GB laptop — measured 20 tok/s on-device.
VKAE (speed): VIDRAFT-optimized serving reaches 18,057 tok/s aggregate on a single B200 (measured).

Engine internals are proprietary; this card reports only measured results and standard open-tool run instructions.

Notes

base_model: Qwen/Qwen3.6-35B-A3B — Darwin-35B-A3B-Mythos is a VIDRAFT derivative of that base.
Benchmarks are labeled by method (greedy vs maj@8); do not compare across methods.
Not multimodal in v1 (text-only). Do not use for tasks requiring vision until the vision build ships.

Downloads last month: 28

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

1-bit

2-bit

3-bit

4-bit

Model tree for VIDraft/Darwin-35B-A3B-Mythos

Base model

Qwen/Qwen3.6-35B-A3B

Quantized

(650)

this model