Instructions to use Irfanuruchi/Qwen3-4B-Computer-Science-Models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Irfanuruchi/Qwen3-4B-Computer-Science-Models with Transformers:

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

pipe = pipeline("text-generation", model="Irfanuruchi/Qwen3-4B-Computer-Science-Models")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Irfanuruchi/Qwen3-4B-Computer-Science-Models", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Irfanuruchi/Qwen3-4B-Computer-Science-Models with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Irfanuruchi/Qwen3-4B-Computer-Science-Models"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Irfanuruchi/Qwen3-4B-Computer-Science-Models",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Irfanuruchi/Qwen3-4B-Computer-Science-Models

SGLang

How to use Irfanuruchi/Qwen3-4B-Computer-Science-Models 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 "Irfanuruchi/Qwen3-4B-Computer-Science-Models" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Irfanuruchi/Qwen3-4B-Computer-Science-Models",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Irfanuruchi/Qwen3-4B-Computer-Science-Models" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Irfanuruchi/Qwen3-4B-Computer-Science-Models",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Irfanuruchi/Qwen3-4B-Computer-Science-Models with Docker Model Runner:
```
docker model run hf.co/Irfanuruchi/Qwen3-4B-Computer-Science-Models
```

Irfanuruchi commited on 6 days ago

Commit

9ee712c

verified ·

1 Parent(s): e0393ca

Update README.md

Browse files

Files changed (1) hide show

README.md +38 -22

README.md CHANGED Viewed

@@ -2,7 +2,7 @@
 Official model releases for the **Qwen3-4B-Computer-Science** project.
-This collection contains the available model formats maintained by the project for different inference runtimes and hardware platforms.
 ---
@@ -13,46 +13,62 @@ This collection contains the available model formats maintained by the project f
 | BF16 | ✅ | Transformers |
 | GGUF | ✅ | llama.cpp, Ollama, LM Studio |
 | AWQ | ✅ | Compressed-Tensors compatible runtimes |
 ---
-## Planned Formats
-| Format | Status |
-|---------|:------:|
-| MLX | ⏳ Planned |
-| OpenVINO | ⏳ Planned |
-Additional formats may be added in future releases.
----
-## Included Models
-- **Qwen3-4B-Computer-Science**
-  - Original BF16 release for Transformers and fine-tuning.
-- **Qwen3-4B-Computer-Science-GGUF**
-  - Quantized GGUF releases for llama.cpp-compatible inference.
-- **Qwen3-4B-Computer-Science-AWQ**
-  - Activation-aware Weight Quantization (AWQ) release using the Compressed-Tensors format.
 ---
 ## Purpose
-The goal of this collection is to provide officially maintained releases of the same model architecture in multiple deployment formats while preserving consistent model behavior across supported inference backends.
-Each repository contains its own documentation, integrity verification files, and runtime-specific usage instructions.
 ---
-## Future Releases
-Planned additions include:
-- MLX for Apple Silicon
-- OpenVINO for Intel CPUs and accelerators
-Future formats will be added to this collection as they become available.

 Official model releases for the **Qwen3-4B-Computer-Science** project.
+This collection provides officially maintained releases of the model across multiple inference runtimes and hardware platforms, allowing users to choose the format best suited to their deployment environment.
 ---
 | BF16 | ✅ | Transformers |
 | GGUF | ✅ | llama.cpp, Ollama, LM Studio |
 | AWQ | ✅ | Compressed-Tensors compatible runtimes |
+| MLX 4-bit | ✅ | Apple MLX |
+| MLX 8-bit | ✅ | Apple MLX |
+| MLX BF16 | ✅ | Apple MLX |
+| OpenVINO INT4 | ✅ | OpenVINO + Optimum Intel |
 ---
+## Included Models
+### Qwen3-4B-Computer-Science
+Original BF16 release intended for Hugging Face Transformers, fine-tuning, and general inference.
+### Qwen3-4B-Computer-Science-GGUF
+GGUF release for efficient inference with llama.cpp-compatible runtimes such as Ollama and LM Studio.
+### Qwen3-4B-Computer-Science-AWQ
+Activation-Aware Weight Quantization (AWQ) release using the Compressed-Tensors format for supported inference frameworks.
+### Qwen3-4B-Computer-Science-MLX-4bit
+Optimized 4-bit MLX release for Apple Silicon devices.
+### Qwen3-4B-Computer-Science-MLX-8bit
+Optimized 8-bit MLX release providing a balance between quality and memory usage.
+### Qwen3-4B-Computer-Science-MLX-BF16
+Full-precision BF16 MLX release for maximum inference quality on Apple Silicon.
+### Qwen3-4B-Computer-Science-OpenVINO-INT4
+OpenVINO INT4 release optimized for efficient CPU inference using Intel OpenVINO and Optimum Intel.
 ---
 ## Purpose
+The objective of this collection is to provide officially maintained releases of the same model across multiple deployment formats while preserving consistent behavior and compatibility with their respective inference ecosystems.
+Each repository includes:
+- Documentation
+- Runtime-specific usage examples
+- License information
+- SHA256 integrity verification files
+- Configuration files required for the target runtime
 ---
+## Model Family
+This release family currently includes:
+- ✅ Transformers BF16
+- ✅ GGUF
+- ✅ AWQ
+- ✅ MLX 4-bit
+- ✅ MLX 8-bit
+- ✅ MLX BF16
+- ✅ OpenVINO INT4
+Additional deployment formats may be added in future releases as the ecosystem evolves.