Instructions to use DavidAU/granite-4.1-8b-Brainstone2-Thinking with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DavidAU/granite-4.1-8b-Brainstone2-Thinking with Transformers:

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

pipe = pipeline("text-generation", model="DavidAU/granite-4.1-8b-Brainstone2-Thinking")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DavidAU/granite-4.1-8b-Brainstone2-Thinking")
model = AutoModelForCausalLM.from_pretrained("DavidAU/granite-4.1-8b-Brainstone2-Thinking")
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

vLLM

How to use DavidAU/granite-4.1-8b-Brainstone2-Thinking with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DavidAU/granite-4.1-8b-Brainstone2-Thinking"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DavidAU/granite-4.1-8b-Brainstone2-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DavidAU/granite-4.1-8b-Brainstone2-Thinking

SGLang

How to use DavidAU/granite-4.1-8b-Brainstone2-Thinking 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 "DavidAU/granite-4.1-8b-Brainstone2-Thinking" \
    --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": "DavidAU/granite-4.1-8b-Brainstone2-Thinking",
		"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 "DavidAU/granite-4.1-8b-Brainstone2-Thinking" \
        --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": "DavidAU/granite-4.1-8b-Brainstone2-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use DavidAU/granite-4.1-8b-Brainstone2-Thinking 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 DavidAU/granite-4.1-8b-Brainstone2-Thinking 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 DavidAU/granite-4.1-8b-Brainstone2-Thinking to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for DavidAU/granite-4.1-8b-Brainstone2-Thinking to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="DavidAU/granite-4.1-8b-Brainstone2-Thinking",
    max_seq_length=2048,
)

Docker Model Runner
How to use DavidAU/granite-4.1-8b-Brainstone2-Thinking with Docker Model Runner:
```
docker model run hf.co/DavidAU/granite-4.1-8b-Brainstone2-Thinking
```

Proposal for Coding Model

by netforcetech - opened 2 days ago

Discussion

netforcetech

2 days ago

Could you create such a coding model ?.So that it specializes as much as possible in coding.
DeepSeek-V4-Code-PRO-35B-A3B-Claude-4.7-Opus-Distill-i1-APEX-Thinking-GGUF
"Hello David! We are aiming for the absolute ceiling of local coding performance. We don't want the 'Flash' version – we want the PRO intelligence distilled into a consumer-friendly 35B-A3B MoE body.
The goal is to bake a model that outclasses everything currently available for local dev environments. We need a distillation from Claude 4.7 Opus (Teacher) onto a DeepSeek-V4-PRO base.
Technical requirements for this 'Ultimate' build:
Base: DeepSeek-V4-PRO (flagship weights for maximum code-base knowledge).
Teacher: Claude 4.7 Opus (for state-of-the-art reasoning and logic).
Structure: A3B (Active 3B) MoE architecture to maintain ~20 tok/sec on consumer hardware.
Thinking/Reasoning: Integrated Chain-of-Thought (CoT) tuning. We want the model to 'think' before coding to ensure logic accuracy.
Optimization: APEX (Advanced Precision Extraction) – this is mandatory to protect the high-logic weights during distillation and prevent 'code-rot' during expert switching.
Target Size: ~35B total parameters.
The community is ready. Once the Safetensors are cooked, mradermacher is already on standby to perform the i1-GGUF (Q5_K_M) quantization for LM Studio users.
David, can you help us create this monster? It would be the definitive tool for every local developer in 2026."

DavidAU

Owner 2 days ago

See PM sent via Discord.; thanks ;

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment