Instructions to use jc-builds/Seed-Coder-8B-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use jc-builds/Seed-Coder-8B-Instruct-GGUF 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 jc-builds/Seed-Coder-8B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf jc-builds/Seed-Coder-8B-Instruct-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jc-builds/Seed-Coder-8B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf jc-builds/Seed-Coder-8B-Instruct-GGUF: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 jc-builds/Seed-Coder-8B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf jc-builds/Seed-Coder-8B-Instruct-GGUF: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 jc-builds/Seed-Coder-8B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jc-builds/Seed-Coder-8B-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/jc-builds/Seed-Coder-8B-Instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use jc-builds/Seed-Coder-8B-Instruct-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/jc-builds/Seed-Coder-8B-Instruct-GGUF:Q4_K_M

Ollama
How to use jc-builds/Seed-Coder-8B-Instruct-GGUF with Ollama:
```
ollama run hf.co/jc-builds/Seed-Coder-8B-Instruct-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use jc-builds/Seed-Coder-8B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/jc-builds/Seed-Coder-8B-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use jc-builds/Seed-Coder-8B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jc-builds/Seed-Coder-8B-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Seed-Coder-8B-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

Seed-Coder-8B-Instruct — GGUF (Apple Silicon-optimized)

A GGUF quantization of ByteDance-Seed/Seed-Coder-8B-Instruct for on-device code generation on high-RAM iPhones, iPads, and Apple Silicon Macs via llama.cpp or apps that wrap it.

Hosted by jc-builds for the Haplo ecosystem. Original weights © ByteDance Seed, redistributed under the MIT License declared on the upstream model card.

TL;DR

An 8B open code model from ByteDance Seed, trained on a model-filtered code corpus and instruction-tuned for code generation, editing, and reasoning about code. MIT-licensed with a 32K context. See the upstream model card for benchmarks.

Available quantizations

File	Size	Recommended use
`Seed-Coder-8B-Instruct-Q4_K_M.gguf`	5.07 GB	Default — best size/quality tradeoff

Details


Parameters	8B (dense)
Context window	32K tokens
Architecture	`llama`
Quantization	Q4_K_M
Minimum device	12 GB RAM iPhone, iPad Pro, or Mac

How to use

Download URL:

https://huggingface.co/jc-builds/Seed-Coder-8B-Instruct-GGUF/resolve/main/Seed-Coder-8B-Instruct-Q4_K_M.gguf

llama.cpp

llama-cli -hf jc-builds/Seed-Coder-8B-Instruct-GGUF:Q4_K_M

License

MIT, as declared on the upstream model card. Original model © ByteDance Seed. Full license text: https://opensource.org/licenses/MIT

Downloads last month: -

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

4-bit

Model tree for jc-builds/Seed-Coder-8B-Instruct-GGUF

Base model

ByteDance-Seed/Seed-Coder-8B-Base

Finetuned

ByteDance-Seed/Seed-Coder-8B-Instruct

Quantized

(19)

this model