Instructions to use glogwa68/granite-4.0-h-350m-DISTILL-gemini-think with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use glogwa68/granite-4.0-h-350m-DISTILL-gemini-think with Transformers:

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

pipe = pipeline("text-generation", model="glogwa68/granite-4.0-h-350m-DISTILL-gemini-think")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("glogwa68/granite-4.0-h-350m-DISTILL-gemini-think")
model = AutoModelForCausalLM.from_pretrained("glogwa68/granite-4.0-h-350m-DISTILL-gemini-think", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use glogwa68/granite-4.0-h-350m-DISTILL-gemini-think with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "glogwa68/granite-4.0-h-350m-DISTILL-gemini-think"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "glogwa68/granite-4.0-h-350m-DISTILL-gemini-think",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/glogwa68/granite-4.0-h-350m-DISTILL-gemini-think

SGLang

How to use glogwa68/granite-4.0-h-350m-DISTILL-gemini-think 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 "glogwa68/granite-4.0-h-350m-DISTILL-gemini-think" \
    --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": "glogwa68/granite-4.0-h-350m-DISTILL-gemini-think",
		"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 "glogwa68/granite-4.0-h-350m-DISTILL-gemini-think" \
        --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": "glogwa68/granite-4.0-h-350m-DISTILL-gemini-think",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use glogwa68/granite-4.0-h-350m-DISTILL-gemini-think with Docker Model Runner:
```
docker model run hf.co/glogwa68/granite-4.0-h-350m-DISTILL-gemini-think
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

granite-4.0-h-350m-DISTILL-gemini-think

This model is a fine-tuned version of ibm-granite/granite-4.0-h-350m trained on high-reasoning conversational data from Gemini 3 Pro.

Model Details

Base Model: ibm-granite/granite-4.0-h-350m
Fine-tuning Dataset: TeichAI/gemini-3-pro-preview-high-reasoning-1000x
Context Length: 1048576 tokens
Special Feature: Thinking/Reasoning with <think> tags

Quantized Versions (GGUF)

🔗 GGUF versions available here: granite-4.0-h-350m-DISTILL-gemini-think-GGUF

Format	Size	Use Case
Q2_K	Smallest	Low memory, reduced quality
Q4_K_M	Recommended	Best balance
Q5_K_M	Good	Higher quality
Q8_0	Large	Near lossless
F16	Largest	Original precision

Usage

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("glogwa68/granite-4.0-h-350m-DISTILL-gemini-think")
tokenizer = AutoTokenizer.from_pretrained("glogwa68/granite-4.0-h-350m-DISTILL-gemini-think")

messages = [{"role": "user", "content": "Hello, how are you?"}]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True)
outputs = model.generate(inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Ollama (GGUF)

ollama run hf.co/glogwa68/granite-4.0-h-350m-DISTILL-gemini-think-GGUF:Q4_K_M

llama.cpp

llama-cli --hf-repo glogwa68/granite-4.0-h-350m-DISTILL-gemini-think-GGUF --hf-file granite-4.0-h-350m-distill-gemini-think-q4_k_m.gguf -p "Hello"

Training Details

Epochs: 3
Learning Rate: 2e-5
Batch Size: 1 (with gradient accumulation)
Precision: FP16
Hardware: Multi-GPU with DeepSpeed ZeRO-3

License

Apache 2.0

Downloads last month: 28

Safetensors

Model size

0.3B params

Tensor type

F16

Model tree for glogwa68/granite-4.0-h-350m-DISTILL-gemini-think

Base model

ibm-granite/granite-4.0-h-350m-base

Finetuned

ibm-granite/granite-4.0-h-350m

Finetuned

(12)

this model

Quantizations

1 model

glogwa68
/

granite-4.0-h-350m-DISTILL-gemini-think