Instructions to use simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1", dtype="auto")

llama-cpp-python

How to use simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1",
	filename="gguf/qwen3-coder-simorg-Q3_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 simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1 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 simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1: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 simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1: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 simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1:Q4_K_M

Use Docker

docker model run hf.co/simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1:Q4_K_M

LM Studio
Jan

vLLM

How to use simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1:Q4_K_M

SGLang

How to use simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1 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 "simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1" \
    --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": "simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1",
		"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 "simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1" \
        --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": "simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1 with Ollama:
```
ollama run hf.co/simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1:Q4_K_M
```

Unsloth Studio

How to use simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1 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 simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1 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 simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1 to start chatting

How to use simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1: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": "simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1: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 simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1: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 "simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1: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 simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1 with Docker Model Runner:
```
docker model run hf.co/simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1:Q4_K_M
```

Lemonade

How to use simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1:Q4_K_M

Run and chat with the model

lemonade run user.poc-simorg-coder-30b-a3b-qwen3-lora-v0.1-Q4_K_M

List all available models

lemonade list

Simorg Qwen3-Coder-30B-A3B-Instruct (fine-tuned)

Hugging Face: simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1

Fine-tuned Qwen/Qwen3-Coder-30B-A3B-Instruct for the Simorg programming language.

This repository contains the merged full weights, LoRA adapter, GGUF quantizations, training data, and Ollama Modelfiles.

Model summary

Item	Value
Base model	Qwen/Qwen3-Coder-30B-A3B-Instruct
Architecture	Qwen3 MoE (`Qwen3MoeForCausalLM`) — 30.5B total, 3.3B active
Fine-tuning	QLoRA (PEFT), assistant-only SFT
LoRA targets	`q/k/v/o_proj`, `gate_proj`, `up_proj`, `down_proj`
Merge	LoRA merged into base weights (bf16 Safetensors)
Context	262144 native; trained with max sequence length 4096
License	Apache 2.0 (derivative of Qwen3-Coder)

Repository layout

safetensors/          Merged full model (Hugging Face / transformers)
gguf/                 GGUF quantizations (llama.cpp, Ollama, LM Studio)
lora/                 LoRA adapter only (PEFT)
training-data/        JSON instruction dataset used for SFT
ollama/               Modelfiles for Ollama import
LICENSE               Apache License 2.0
NOTICE                Attribution and modification notice

See MANIFEST.md for the complete file list.

Usage

Transformers (Safetensors)

Point at the safetensors/ folder or download this repo and load from safetensors/:

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = "simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1"  # safetensors/ subfolder or repo root
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True,
)

If the Hub repo keeps weights under safetensors/, pass the subpath:

model_path = "simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1/safetensors"

GGUF (llama.cpp)

Recommended quant: gguf/qwen3-coder-simorg-Q4_K_M.gguf (~17 GB).

llama-cli -m gguf/qwen3-coder-simorg-Q4_K_M.gguf -p "Your prompt"

Ollama

After cloning this repository:

cd ollama
ollama create simorg-qwen3-q4 -f Modelfile-qwen-3-Q4-K-M
ollama run simorg-qwen3-q4

Modelfiles use FROM ../gguf/... — run ollama create from the ollama/ directory.

Modelfile	Quant	Approx. size
`Modelfile-qwen-3-Q4-K-M`	Q4_K_M	~17 GB
`Modelfile-qwen-3-Q5-K-M`	Q5_K_M	~20 GB
`Modelfile-qwen-3-Q3_K_M`	Q3_K_M	~14 GB
`Modelfile-qwen-3-Q4-K-S`	Q4_K_S	~16 GB
`Modelfile-qwen-3-Q6-K`	Q6_K	~23 GB
`Modelfile-qwen-3-Q8-0`	Q8_0	~30 GB

LoRA adapter (PEFT)

Load the adapter from lora/ on top of the base model:

from peft import AutoPeftModelForCausalLM
from transformers import AutoTokenizer

base = "Qwen/Qwen3-Coder-30B-A3B-Instruct"
model = AutoPeftModelForCausalLM.from_pretrained("path/to/lora", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("path/to/lora", trust_remote_code=True)

Training data

Instruction JSON in training-data/ with question and answer fields. Used for supervised fine-tuning on Simorg syntax and patterns.

Training details

Method: QLoRA SFT with TRL SFTTrainer, assistant-only loss
Base: Qwen/Qwen3-Coder-30B-A3B-Instruct
LoRA rank: 16 (attention), 8 (expert MLP); use_rslora=True
Learning rate: 1e-4, cosine schedule, 3 epochs
Max length: 4096 tokens during training

License and attribution

This model is a derivative work of Qwen3-Coder-30B-A3B-Instruct by Alibaba Cloud, licensed under the Apache License 2.0.

See LICENSE for the full license text.
See NOTICE for modification and attribution details.

You may use, modify, and redistribute this model under the terms of Apache 2.0, including commercial use, provided you include the license and state significant modifications.

This repository does not grant permission to use Qwen or Alibaba trademarks in a way that implies endorsement.

Citation

@misc{qwen3technicalreport,
  title={Qwen3 Technical Report},
  author={Qwen Team},
  year={2025},
  eprint={2505.09388},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2505.09388},
}

Disclaimer

Model outputs may be incorrect or incomplete. This is a PoC model, fine-tuned on top of a PoC version of Simorg Programming Language! Please don't use it in a production environment and wait for the first LTS version.

Downloads last month: 177

GGUF

Model size

31B params

Architecture

qwen3moe

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

Model tree for simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1

Base model

Qwen/Qwen3-Coder-30B-A3B-Instruct

Adapter

(52)

this model

Paper for simorg-platform/poc-simorg-coder-30b-a3b-qwen3-lora-v0.1

Qwen3 Technical Report

Paper • 2505.09388 • Published May 14, 2025 • 343