Instructions to use shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF with Transformers:

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

pipe = pipeline("image-text-to-text", model="shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF", dtype="auto")

llama-cpp-python

How to use shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF",
	filename="gemma-4-31b-claude-4.6-opus-thinking-distilled-s7-q8_0.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF:Q8_0

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 shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF:Q8_0

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 shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF:Q8_0

Use Docker

docker model run hf.co/shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF:Q8_0

LM Studio
Jan

vLLM

How to use shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF:Q8_0

SGLang

How to use shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF 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 "shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF" \
    --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": "shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF",
		"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 "shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF" \
        --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": "shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF with Ollama:
```
ollama run hf.co/shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF:Q8_0
```

Unsloth Studio new

How to use shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF 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 shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF 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 shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF to start chatting

Docker Model Runner
How to use shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF with Docker Model Runner:
```
docker model run hf.co/shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF:Q8_0
```

Lemonade

How to use shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull shreyan35/gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF:Q8_0

Run and chat with the model

lemonade run user.gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF-Q8_0

List all available models

lemonade list

gemma-4-31b-claude-opus-4.6-thinking-distilled-s7-GGUF / README.md

shreyan35

Update README.md

442018d verified about 1 month ago

preview code

raw

history blame contribute delete

2.16 kB

	---
	license: mit
	base_model:
	- google/gemma-4-31B-it
	library_name: transformers
	tags:
	- gemma4
	- gemma
	- reasoning
	- claude-opus
	- distillation
	- full-finetune
	- llm
	- mlm
	- multimodal
	- video
	- text
	- audio
	- vision
	language:
	- en
	pipeline_tag: image-text-to-text
	model_name: gemma-4-31B-Claude-4.6-Opus-thinking-distilled-s7
	parameter_count: 30700000000
	---

	# gemma-4-31B-Claude-4.6-Opus-thinking-distilled-s7-multimodal
	<div align="center">
	<img src="https://huggingface.co/shreyan35/gemma-4-31B-Claude-4.6-Opus-thinking-distilled-s7/resolve/main/banner.jpeg" width="100%" alt="S7 Banner">
	</div>

	_This new release now makes this finetune listed and tuned correctly for multimodality, now ultra capable_

	Full parameter fine-tune of gemma 4 31b on ~12,000 Claude Opus 4.6 reasoning traces. This is a indigenously made special model


	## Highlights

	- ~90% token accuracy after 4 epochs
	- Full parameter SFT, not LoRA
	- 12,000 pure Claude Opus 4.6 traces — consistent reasoning style, no mixed-model data
	- Native Gemma 4 thinking format — uses standard built-in thinking tokens
	## Excellent Performance
	### Reasoning & Knowledge
	\| Benchmark \| S7 Score \|
	\| :--- \| :--- \|
	\| MMLU Pro \| 90.3% \|
	\| GPQA Diamond \| 89.4% \|
	\| BigBench Extra Hard \| 78.9% \|
	\| MMMLU (Multilingual) \| 93.7% \|
	\| HLE (no tools) \| 20.7% \|
	\| HLE (with search) \| 28.1% \|

	### Mathematics & Coding
	\| Benchmark \| S7 Score \|
	\| :--- \| :--- \|
	\| AIME 2026 (no tools) \| 94.6% \|
	\| LiveCodeBench v6 \| 84.8% \|
	\| Codeforces ELO \| 2279 \|
	\| HumanEval \| 96.7% \|
	\| MBPP Plus \| 94.0% \|

	### Multimodal (Vision & Medical)
	\| Benchmark \| S7 Score \|
	\| :--- \| :--- \|
	\| MMMU Pro \| 81.5% \|
	\| MATH-Vision \| 90.7% \|
	\| MedXPertQA MM \| 65.0% \|

	### Agentic & Long Context
	\| Benchmark \| S7 Score \|
	\| :--- \| :--- \|
	\| τ²-bench (Average) \| 81.5% \|
	\| τ²-bench (Retail) \| 91.6% \|
	\| MRCR v2 (8-needle 128k) \| 70.4% \|

	Overall Improvement - 6%

	## Model Specifications

	- Parameters: 30.7B (Dense)
	- Architecture: 60 Layers
	- Context Window: 256K tokens
	- Vocabulary Size: 262,144
	- Native Modalities: Text, Image, Video (Frame sequences)