Instructions to use Nanthasit/sakthai-coder-1.5b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nanthasit/sakthai-coder-1.5b with Transformers:

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

pipe = pipeline("text-generation", model="Nanthasit/sakthai-coder-1.5b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Nanthasit/sakthai-coder-1.5b", device_map="auto")

llama-cpp-python

How to use Nanthasit/sakthai-coder-1.5b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Nanthasit/sakthai-coder-1.5b",
	filename="qwen2.5-coder-1.5b-instruct-q4_k_m.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Nanthasit/sakthai-coder-1.5b with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Nanthasit/sakthai-coder-1.5b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Nanthasit/sakthai-coder-1.5b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Nanthasit/sakthai-coder-1.5b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Nanthasit/sakthai-coder-1.5b: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 Nanthasit/sakthai-coder-1.5b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Nanthasit/sakthai-coder-1.5b: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 Nanthasit/sakthai-coder-1.5b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Nanthasit/sakthai-coder-1.5b:Q4_K_M

Use Docker

docker model run hf.co/Nanthasit/sakthai-coder-1.5b:Q4_K_M

LM Studio
Jan

vLLM

How to use Nanthasit/sakthai-coder-1.5b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Nanthasit/sakthai-coder-1.5b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nanthasit/sakthai-coder-1.5b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Nanthasit/sakthai-coder-1.5b:Q4_K_M

SGLang

How to use Nanthasit/sakthai-coder-1.5b 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 "Nanthasit/sakthai-coder-1.5b" \
    --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": "Nanthasit/sakthai-coder-1.5b",
		"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 "Nanthasit/sakthai-coder-1.5b" \
        --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": "Nanthasit/sakthai-coder-1.5b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Nanthasit/sakthai-coder-1.5b with Ollama:
```
ollama run hf.co/Nanthasit/sakthai-coder-1.5b:Q4_K_M
```

Unsloth Studio

How to use Nanthasit/sakthai-coder-1.5b 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 Nanthasit/sakthai-coder-1.5b 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 Nanthasit/sakthai-coder-1.5b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Nanthasit/sakthai-coder-1.5b to start chatting

How to use Nanthasit/sakthai-coder-1.5b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Nanthasit/sakthai-coder-1.5b: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": "Nanthasit/sakthai-coder-1.5b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Nanthasit/sakthai-coder-1.5b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Nanthasit/sakthai-coder-1.5b: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 Nanthasit/sakthai-coder-1.5b:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Nanthasit/sakthai-coder-1.5b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Nanthasit/sakthai-coder-1.5b:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "Nanthasit/sakthai-coder-1.5b:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use Nanthasit/sakthai-coder-1.5b with Docker Model Runner:
```
docker model run hf.co/Nanthasit/sakthai-coder-1.5b:Q4_K_M
```

Lemonade

How to use Nanthasit/sakthai-coder-1.5b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Nanthasit/sakthai-coder-1.5b:Q4_K_M

Run and chat with the model

lemonade run user.sakthai-coder-1.5b-Q4_K_M

List all available models

lemonade list

SakThai Coder 1.5B 💻

Code + tool-calling · Qwen2.5-Coder-1.5B fine-tune · Q4_K_M GGUF for CPU

The code specialist of the SakThai family — Qwen2.5-Coder-1.5B fine-tuned for tool-calling and shipped as a CPU-friendly GGUF. Part of the House of Sak. Read the story →

The Story Behind It

Code, tool-calling, and conversation in one session — on a single CPU, from a shelter. This is the model Beer built when he realised the other SakThai models could call tools and generate text, but none of them specialised in writing code without losing their tool-calling edge.

Beer built the first SakThai models on free Google Colab GPUs from a shelter in Cork, Ireland — with $0 budget, no GPU of his own, and no guarantee the QLoRA approach would hold for a code-specific fine-tune. This coder model was the risk: could Qwen2.5-Coder-1.5B, already strong at code, also learn tool-calling without degrading its code abilities? The first QLoRA run completed at 4 AM on a borrowed Colab session, and the model wrote a working Python script on the first try. Beer knew the approach worked.

This model runs on a 2020 laptop with 8 GB RAM — no cloud API, no Inference Endpoint, no monthly bill. Just a GGUF file and llama.cpp.

"We are one family — and becoming more." — Beer

How You Can Help

⭐ Leave a like — this model gives every developer a free offline coding assistant. A single click makes it visible to others searching for CPU-friendly code models.
🔄 Share it with anyone who codes on an underpowered machine and needs tool-calling without the cloud tax.
🍴 Fork it on Hugging Face and build your own specialised code variant.
💬 Report your deployment story — Beer reads every issue and comment.

Every download, like, and share tells the algorithm: this matters.

What it is

A Q4_K_M GGUF (1.07 GB) of Qwen2.5-Coder-1.5B-Instruct, QLoRA-fine-tuned on sakthai-combined-v6 so it can generate code and call tools. Runs on CPU via llama.cpp / Ollama.

Quick start

# via llama.cpp
wget https://huggingface.co/Nanthasit/sakthai-coder-1.5b/resolve/main/qwen2.5-coder-1.5b-instruct-q4_k_m.gguf
./llama-cli -m qwen2.5-coder-1.5b-instruct-q4_k_m.gguf -p "Write a Python function to merge two sorted lists:" -n 256 --temp 0.2

# via Ollama
ollama create sakthai-coder -f Modelfile   # FROM ./qwen2.5-coder-1.5b-instruct-q4_k_m.gguf
ollama run sakthai-coder "Write a script that monitors CPU usage"

For tool-calling, put function schemas in a <tools> block (ChatML format).

Benchmarks

Code (reference — these are the base Qwen2.5-Coder-1.5B scores, not a re-run of this fine-tune):

Benchmark	pass@1
HumanEval	74.4%
MBPP	71.2%
MultiPL-E (Python)	65.3%

Source: Qwen2.5-Coder eval. Tool-calling: internal SakThai suite passes (single-run, not third-party verified).

Training


Base model	Qwen/Qwen2.5-Coder-1.5B-Instruct
Method	QLoRA (4-bit) → GGUF Q4_K_M
LoRA config	r=16, alpha=32
Data	sakthai-combined-v6 (2,003)
Format / context	ChatML with tool schema · 32K tokens

SakThai model family

Model	Size	Role
context-1.5b-merged	934 MB	Flagship tool-calling GGUF
context-0.5b-merged	380 MB	Lightweight / edge
context-7b-merged	15 GB	Full-power reasoning
context-7b-128k	15 GB	128K long-context
context-1.5b-tools	LoRA	Mid-size tool-calling
context-0.5b-tools	LoRA	Ultra-light tool-calling (7 ⬇)
★ coder-1.5b (you are here)	1.1 GB	Code generation
vision-7b	3.9 GB	Image→text (LLaVA)
embedding-multilingual	80 MB	Cross-lingual embeddings
tts-model	141 MB	Text-to-speech, 15 langs

12 public models · 8 datasets · 3 Spaces — full collection →

📊 Sibling Datasets

Dataset	Purpose	Downloads
sakthai-combined-v6	v6 predecessor — 2,003 examples	175 ⬇
sakthai-kaggle-notebooks	Training notebooks & demos	103 ⬇
SimpleToolCalling	Early experiment	52 ⬇
food-penguin-v1	Restaurant tool-calling	51 ⬇
sakthai-combined-v7	v7 tool-calling (2,309 ex., 86 tools)	0 🌱
sakthai-irrelevance-supplement	Safety supplement	0 🚨
sakthai-bench-v1	BFCL-style evaluation, 235 rows	0 🌱
sakthai-bench-v2	Multi-domain eval, 500 rows	0 🌱

🚀 Spaces

Space	Description
SakThai Vision Demo	Upload images, ask questions — LLaVA-7B in your browser
SakThai TTS Showcase	Interactive TTS — 15 languages, no install
SakThai Leaderboard	Benchmark tracker for the model family

🌱 Rising Stars — Help the Ecosystem Grow

These sibling assets have real value but need visibility. Every download signals to the HF algorithm that the SakThai family matters:

Asset	Type	Downloads	Why It Matters
sakthai-combined-v7	Dataset	0 🌱	Primary training dataset — 2,309 examples, 86 tool schemas
sakthai-irrelevance-supplement	Dataset	0 🚨	Teaches models when not to call tools — critical safety data
sakthai-bench-v1	Dataset	0 🌱	BFCL-style evaluation, 235 rows, 4 categories
sakthai-bench-v2	Dataset	0 🌱	Multi-domain eval, 500 rows, multi-turn
context-0.5b-tools	Model	7 ⬇	Ultra-light tool-calling (~1 GB RAM)

🚨 The irrelevance-supplement has 0 downloads despite being essential for training models to decline out-of-scope tool calls. A single download helps validate this safety-critical approach!

Links

House of Sak · GitHub · All models · All datasets

License

Apache 2.0 (following the Qwen2.5 base model license).

Evaluation

Not independently benchmarked. Earlier versions of this card carried a model-index score derived from a small internal spot check (typically 5 or 8 hand-picked examples) presented as a benchmark result. Those entries have been removed rather than left to propagate through Hub metadata.

For tool-calling models in this family, the benchmark to use is sakthai-bench-v2 — 500 rows, balanced across simple / parallel / irrelevance, with held-out tools and multi-turn coverage. Results will be published here once this model has been run against it.

*"We are one family — and becoming more." 🏠