Instructions to use Rumiii/Qwen3-8B-MedReasonPath with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Rumiii/Qwen3-8B-MedReasonPath with Transformers:

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

pipe = pipeline("text-generation", model="Rumiii/Qwen3-8B-MedReasonPath")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Rumiii/Qwen3-8B-MedReasonPath")
model = AutoModelForCausalLM.from_pretrained("Rumiii/Qwen3-8B-MedReasonPath", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Rumiii/Qwen3-8B-MedReasonPath 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 Rumiii/Qwen3-8B-MedReasonPath:Q8_0
# Run inference directly in the terminal:
llama cli -hf Rumiii/Qwen3-8B-MedReasonPath:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Rumiii/Qwen3-8B-MedReasonPath:Q8_0
# Run inference directly in the terminal:
llama cli -hf Rumiii/Qwen3-8B-MedReasonPath:Q8_0

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf Rumiii/Qwen3-8B-MedReasonPath:Q8_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf Rumiii/Qwen3-8B-MedReasonPath:Q8_0

Use Docker

docker model run hf.co/Rumiii/Qwen3-8B-MedReasonPath:Q8_0

Llama new
LM Studio
Jan

vLLM

How to use Rumiii/Qwen3-8B-MedReasonPath with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Rumiii/Qwen3-8B-MedReasonPath"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rumiii/Qwen3-8B-MedReasonPath",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Rumiii/Qwen3-8B-MedReasonPath:Q8_0

SGLang

How to use Rumiii/Qwen3-8B-MedReasonPath 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 "Rumiii/Qwen3-8B-MedReasonPath" \
    --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": "Rumiii/Qwen3-8B-MedReasonPath",
		"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 "Rumiii/Qwen3-8B-MedReasonPath" \
        --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": "Rumiii/Qwen3-8B-MedReasonPath",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Rumiii/Qwen3-8B-MedReasonPath with Ollama:
```
ollama run hf.co/Rumiii/Qwen3-8B-MedReasonPath:Q8_0
```
Unsloth Desktop

How to use Rumiii/Qwen3-8B-MedReasonPath with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Rumiii/Qwen3-8B-MedReasonPath:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Rumiii/Qwen3-8B-MedReasonPath:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Rumiii/Qwen3-8B-MedReasonPath with Docker Model Runner:
```
docker model run hf.co/Rumiii/Qwen3-8B-MedReasonPath:Q8_0
```

Lemonade

How to use Rumiii/Qwen3-8B-MedReasonPath with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Rumiii/Qwen3-8B-MedReasonPath:Q8_0

Run and chat with the model

lemonade run user.Qwen3-8B-MedReasonPath-Q8_0

List all available models

lemonade list

Hermes Agent

How to use Rumiii/Qwen3-8B-MedReasonPath with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Rumiii/Qwen3-8B-MedReasonPath:Q8_0

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 Rumiii/Qwen3-8B-MedReasonPath:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Rumiii/Qwen3-8B-MedReasonPath with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Rumiii/Qwen3-8B-MedReasonPath:Q8_0

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 "Rumiii/Qwen3-8B-MedReasonPath:Q8_0" \
  --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"

Qwen3-8B-MedReasonPath

Qwen3-8B fine-tuned for stronger step-by-step medical reasoning, built to retain its native thinking mode and its existing tool-calling ability.

This is a full standalone model. No PEFT, no Unsloth, no extra libraries required — load it exactly like any other transformers causal LM.

Base model

Qwen/Qwen3-8B — 8.2B parameters, hybrid thinking / non-thinking model with native agentic tool-calling support.

Training data

MedReason (5,000 examples) — knowledge-graph grounded medical reasoning, for clinical reasoning quality.
xLAM Function-Calling (681 examples) — general tool-calling data, mixed in during training to help preserve agentic behavior.

Method

QLoRA fine-tuning (4-bit, rank 16, alpha 32) on a single T4 GPU, using Unsloth purely as a training-time tool. The resulting adapter was merged into the base model and released here as a full fp16 checkpoint — Unsloth is not needed to use this model, only transformers.

Result

Improved step-by-step reasoning inside Qwen3-8B's native <think>...</think> mode on medical/clinical questions, while keeping thinking mode, non-thinking mode, and tool-calling all functional.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "Rumiii/Qwen3-8B-MedReasonPath", torch_dtype="auto", device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("Rumiii/Qwen3-8B-MedReasonPath")

messages = [{"role": "user", "content": "What causes aortic dissection?"}]
text = tokenizer.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True, enable_thinking=True
)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=600, temperature=0.6, top_p=0.95, top_k=20)
print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))

Set enable_thinking=False for direct, non-reasoning answers.

License

Apache 2.0, matching the base model.

Disclaimer

Research and educational project. Not validated for clinical use — not a substitute for professional medical advice.

GGUF

An 8-bit quantized GGUF version (Qwen3-8B-MedReasonPath-Q8_0.gguf, ~8.7GB) is also available in this repo, for use with llama.cpp, Ollama, or LM Studio.

# llama.cpp
./llama-cli -hf Rumiii/Qwen3-8B-MedReasonPath:Q8_0

Downloads last month: 92

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for Rumiii/Qwen3-8B-MedReasonPath

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Quantized

(488)

this model

Quantizations

2 models

Rumiii
/

Qwen3-8B-MedReasonPath

Qwen3-8B-MedReasonPath

Base model

Training data

Method

Result

Usage

License

Disclaimer

GGUF

Model tree for Rumiii/Qwen3-8B-MedReasonPath

Dataset used to train Rumiii/Qwen3-8B-MedReasonPath