Instructions to use jaigouk/smollm3-german-teacher with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jaigouk/smollm3-german-teacher with Transformers:

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

pipe = pipeline("text-generation", model="jaigouk/smollm3-german-teacher")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("jaigouk/smollm3-german-teacher", dtype="auto")

llama-cpp-python

How to use jaigouk/smollm3-german-teacher with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="jaigouk/smollm3-german-teacher",
	filename="smollm3-german-teacher-q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use jaigouk/smollm3-german-teacher with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf jaigouk/smollm3-german-teacher:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf jaigouk/smollm3-german-teacher:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf jaigouk/smollm3-german-teacher:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf jaigouk/smollm3-german-teacher: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 jaigouk/smollm3-german-teacher:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf jaigouk/smollm3-german-teacher: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 jaigouk/smollm3-german-teacher:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jaigouk/smollm3-german-teacher:Q4_K_M

Use Docker

docker model run hf.co/jaigouk/smollm3-german-teacher:Q4_K_M

LM Studio
Jan

vLLM

How to use jaigouk/smollm3-german-teacher with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jaigouk/smollm3-german-teacher"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jaigouk/smollm3-german-teacher",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jaigouk/smollm3-german-teacher:Q4_K_M

SGLang

How to use jaigouk/smollm3-german-teacher 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 "jaigouk/smollm3-german-teacher" \
    --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": "jaigouk/smollm3-german-teacher",
		"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 "jaigouk/smollm3-german-teacher" \
        --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": "jaigouk/smollm3-german-teacher",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use jaigouk/smollm3-german-teacher with Ollama:
```
ollama run hf.co/jaigouk/smollm3-german-teacher:Q4_K_M
```

Unsloth Studio new

How to use jaigouk/smollm3-german-teacher 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 jaigouk/smollm3-german-teacher 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 jaigouk/smollm3-german-teacher to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for jaigouk/smollm3-german-teacher to start chatting

Pi new

How to use jaigouk/smollm3-german-teacher with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf jaigouk/smollm3-german-teacher: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": "jaigouk/smollm3-german-teacher:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use jaigouk/smollm3-german-teacher with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf jaigouk/smollm3-german-teacher: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 jaigouk/smollm3-german-teacher:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use jaigouk/smollm3-german-teacher with Docker Model Runner:
```
docker model run hf.co/jaigouk/smollm3-german-teacher:Q4_K_M
```

Lemonade

How to use jaigouk/smollm3-german-teacher with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jaigouk/smollm3-german-teacher:Q4_K_M

Run and chat with the model

lemonade run user.smollm3-german-teacher-Q4_K_M

List all available models

lemonade list

SmolLM3 German Teacher V6 (λ=2500)

A finetuned 3B parameter model specialized for teaching German at A1-B1 levels, optimized for grammatical accuracy using Elastic Weight Consolidation (EWC).

Model Details

Property	Value
Base Model	HuggingFaceTB/SmolLM3-3B
Training Method	QLoRA + EWC (Two-Stage Continual Learning)
Training Data	~1,800 examples (900 per stage)
EWC Lambda	2500 (best from grid search)
Hardware	RTX 4090 (24GB VRAM)

Evaluation Results

Metric	V6 (This Model)	V5 Baseline	Improvement
CoLA MCC	0.6236	0.5927	+5.2%
GEC Macro F1	0.1909	0.1121	+70.3%
Generation Quality	3.29/5.0	3.71/5.0	-11.3%
Overall Score	0.5158	0.4987	+3.4%

Why V6?

We tested multiple approaches (V5-V9) to balance accuracy and fluency:

Model	Method	CoLA MCC	GEC F1	Generation	Overall	Status
V5	EWC Baseline	0.5927	0.1121	3.71	0.4987	Reference
V6	EWC λ=2500	0.6236	0.1909	3.29	0.5158	Best
V7	Multi-Task SFT	0.3333	0.0479	3.00	0.3858	Failed
V8	DPO	0.5833	0.0625	3.63	0.4730	Failed
V9	SimPO	0.5674	0.0731	3.72	0.4787	Failed

V6 has the best grammatical accuracy, which is critical for a German teacher model. Preference optimization (V8/V9) improved fluency but destroyed accuracy.

Capabilities

German grammar correction with clear explanations
Error identification: haben/sein in Perfekt, article gender, case endings, word order
A1-B1 level instruction following CEFR guidelines
Bilingual explanations (German/English)

Files

File	Size	Quantization	VRAM Required
`smollm3-german-teacher-v6-q4_k_m.gguf`	1.9 GB	Q4_K_M	~3 GB

Usage

With Ollama

# Download and create model
ollama create smollm3-german:v6 -f - <<EOF
FROM ./smollm3-german-teacher-v6-q4_k_m.gguf

TEMPLATE """{{- if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{- range .Messages }}<|im_start|>{{ .Role }}
{{ .Content }}<|im_end|>
{{ end }}<|im_start|>assistant
"""

SYSTEM """You are a friendly German language teacher specializing in A1-B1 level instruction. Help students learn German grammar, correct mistakes with clear explanations, and provide examples."""

PARAMETER stop "<|im_end|>"
PARAMETER temperature 0.7
EOF

# Use
ollama run smollm3-german:v6 "Korrigiere: Ich habe nach Berlin gefahren."

With llama.cpp

./llama-cli -m smollm3-german-teacher-v6-q4_k_m.gguf \
  -p "<|im_start|>user\nKorrigiere: Ich habe nach Berlin gefahren.<|im_end|>\n<|im_start|>assistant\n" \
  -n 256 --temp 0.7

With Transformers (Full Model)

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("jaigouk/smollm3-german-teacher")
tokenizer = AutoTokenizer.from_pretrained("jaigouk/smollm3-german-teacher")

prompt = "Korrigiere: Ich habe nach Berlin gefahren."
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0]))

Example Output

Input: Korrigiere: Ich habe nach Berlin gefahren.

Output:

Die korrekte Form ist: "Ich bin nach Berlin gefahren."

Erklärung: Bei Verben der Bewegung (fahren, gehen, kommen, fliegen) verwendet man im Perfekt das Hilfsverb "sein", nicht "haben".

Regel: Bewegungsverben + sein = Perfekt

Ich bin gefahren (nicht: Ich habe gefahren)

Ich bin gegangen

Ich bin gekommen

Training Details

Two-Stage EWC Training

Stage 1: Grammar fundamentals (articles, cases, verb conjugation)
Stage 2: Error correction and explanations with EWC regularization

EWC (Elastic Weight Consolidation)

EWC prevents catastrophic forgetting by:

Computing Fisher Information Matrix after Stage 1
Using Fisher as importance weights during Stage 2
Loss: L_total = L_task + λ * L_ewc

Lambda=2500 was selected from grid search over [2500, 5000, 10000].

Hyperparameters

# Stage 1 & 2
learning_rate = 2e-5
batch_size = 4
epochs = 3
lora_r = 16
lora_alpha = 32

# EWC
ewc_lambda = 2500
fisher_samples = 500

Limitations

Optimized for A1-B1 level; may struggle with advanced grammar (C1+)
Generation fluency is lower than V8/V9 (trade-off for accuracy)
Best for structured grammar tasks; less natural in open conversation
German/English bilingual; other languages not supported

Citation

@misc{smollm3-german-teacher-v6,
  author = {Jaigouk Kim},
  title = {SmolLM3 German Teacher V6: EWC-Optimized Grammar Instruction Model},
  year = {2025},
  publisher = {HuggingFace},
  url = {https://huggingface.co/jaigouk/smollm3-german-teacher}
}

Acknowledgments

HuggingFace for SmolLM3 base model
Unsloth for efficient QLoRA training
llama.cpp for GGUF conversion

License

Apache 2.0 (same as base model)

Downloads last month: 56

GGUF

Model size

3B params

Architecture

smollm3

Hardware compatibility

4-bit

8-bit

Model tree for jaigouk/smollm3-german-teacher

Base model

HuggingFaceTB/SmolLM3-3B-Base

Finetuned

HuggingFaceTB/SmolLM3-3B

Quantized

(72)

this model

Evaluation results

MCC
self-reported

0.624
Macro F1
self-reported

0.191
Score
self-reported

3.290