Instructions to use unsloth/Seed-OSS-36B-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/Seed-OSS-36B-Instruct-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="unsloth/Seed-OSS-36B-Instruct-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("unsloth/Seed-OSS-36B-Instruct-GGUF", dtype="auto")

llama-cpp-python

How to use unsloth/Seed-OSS-36B-Instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="unsloth/Seed-OSS-36B-Instruct-GGUF",
	filename="BF16/Seed-OSS-36B-Instruct-BF16-00001-of-00002.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 unsloth/Seed-OSS-36B-Instruct-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf unsloth/Seed-OSS-36B-Instruct-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf unsloth/Seed-OSS-36B-Instruct-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf unsloth/Seed-OSS-36B-Instruct-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf unsloth/Seed-OSS-36B-Instruct-GGUF:UD-Q4_K_XL

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 unsloth/Seed-OSS-36B-Instruct-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/Seed-OSS-36B-Instruct-GGUF:UD-Q4_K_XL

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 unsloth/Seed-OSS-36B-Instruct-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/Seed-OSS-36B-Instruct-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/Seed-OSS-36B-Instruct-GGUF:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use unsloth/Seed-OSS-36B-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/Seed-OSS-36B-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": "unsloth/Seed-OSS-36B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/Seed-OSS-36B-Instruct-GGUF:UD-Q4_K_XL

SGLang

How to use unsloth/Seed-OSS-36B-Instruct-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 "unsloth/Seed-OSS-36B-Instruct-GGUF" \
    --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": "unsloth/Seed-OSS-36B-Instruct-GGUF",
		"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 "unsloth/Seed-OSS-36B-Instruct-GGUF" \
        --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": "unsloth/Seed-OSS-36B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use unsloth/Seed-OSS-36B-Instruct-GGUF with Ollama:
```
ollama run hf.co/unsloth/Seed-OSS-36B-Instruct-GGUF:UD-Q4_K_XL
```

Unsloth Studio

How to use unsloth/Seed-OSS-36B-Instruct-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 unsloth/Seed-OSS-36B-Instruct-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 unsloth/Seed-OSS-36B-Instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for unsloth/Seed-OSS-36B-Instruct-GGUF to start chatting

How to use unsloth/Seed-OSS-36B-Instruct-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf unsloth/Seed-OSS-36B-Instruct-GGUF:UD-Q4_K_XL

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": "unsloth/Seed-OSS-36B-Instruct-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use unsloth/Seed-OSS-36B-Instruct-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf unsloth/Seed-OSS-36B-Instruct-GGUF:UD-Q4_K_XL

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 unsloth/Seed-OSS-36B-Instruct-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Docker Model Runner
How to use unsloth/Seed-OSS-36B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/Seed-OSS-36B-Instruct-GGUF:UD-Q4_K_XL
```

Lemonade

How to use unsloth/Seed-OSS-36B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/Seed-OSS-36B-Instruct-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.Seed-OSS-36B-Instruct-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Can not run it on llamacpp + Mac m4

by danielfl - opened Aug 25, 2025

Discussion

danielfl

Aug 25, 2025

Just tried this model on a Macbook Air M4 with 24GB of RAM:

./llama-server --port 8888 -ngl 99 -hf unsloth/Seed-OSS-36B-Instruct-GGUF:Q2_K_XL

the model seems to load but when I send a command using the interface I get nothing in return.

{# Copyright 2025-present Unsloth. Apache 2.0 License. #}, example_format: 'seed:bossystem
You are a helpful assistantseed:eos seed:bosuser
Helloseed:eos seed:bosassistant
Hi thereseed:eos seed:bosuser
How are you?seed:eos seed:bosassistant
'
main: server is listening on http://127.0.0.1:8888 - starting the main loop
srv update_slots: all slots are idle
srv params_from_: Chat format: Content-only
slot launch_slot_: id 0 | task 0 | processing task
slot update_slots: id 0 | task 0 | new prompt, n_ctx_slot = 4096, n_keep = 0, n_prompt_tokens = 64
slot update_slots: id 0 | task 0 | kv cache rm [0, end)
slot update_slots: id 0 | task 0 | prompt processing progress, n_past = 64, n_tokens = 64, progress = 1.000000
slot update_slots: id 0 | task 0 | prompt done, n_past = 64, n_tokens = 64

CHAT:

main: interactive mode on.
sampler seed: 2428926723
sampler params:
repeat_last_n = 64, repeat_penalty = 1,000, frequency_penalty = 0,000, presence_penalty = 0,000
dry_multiplier = 0,000, dry_base = 1,750, dry_allowed_length = 2, dry_penalty_last_n = 4096
top_k = 40, top_p = 0,950, min_p = 0,050, xtc_probability = 0,000, xtc_threshold = 0,100, typical_p = 1,000, top_n_sigma = -1,000, temp = 0,800
mirostat = 0, mirostat_lr = 0,100, mirostat_ent = 5,000
sampler chain: logits -> logit-bias -> penalties -> dry -> top-n-sigma -> top-k -> typical -> top-p -> min-p -> xtc -> temp-ext -> dist
generate: n_ctx = 4096, n_batch = 2048, n_predict = -1, n_keep = 0

== Running in interactive mode. ==

Press Ctrl+C to interject at any time.
Press Return to return control to the AI.
To return control without starting a new line, end your input with '/'.
If you want to submit another line, end your input with ''.
Not using system message. To change it, set a different value via -sys PROMPT

hello

verbose:

embd_inp.size(): 0, n_consumed: 0
waiting for user input

wazzup
buffer: 'wazzup'
formatted: 'seed:bosuser
wazzupseed:eos seed:bosassistant
'
input tokens: [ 'seed:bos':0, 'user':4169, '
':326, 'w':214, 'azz':12543, 'up':1496, 'seed:eos':2, 'seed:bos':0, 'ass':712, 'istant':14300, '
':326 ]
n_remain: -12
embd_inp.size(): 11, n_consumed: 0
eval: [ 'seed:bos':0, 'user':4169, '
':326, 'w':214, 'azz':12543, 'up':1496, 'seed:eos':2, 'seed:bos':0, 'ass':712, 'istant':14300, '
':326 ]
n_past = 11
n_remain: -13
eval: [ '<[PLHD31_never_used]>':31 ]
n_past = 12
n_remain: -14
eval: [ '<[PLHD31_never_used]>':31 ]
n_past = 13
n_remain: -15
eval: [ '<[PLHD31_never_used]>':31 ]
n_past = 14
n_remain: -16
eval: [ '<[PLHD31_never_used]>':31 ]
n_past = 15
n_remain: -17

ox-ox

Aug 27, 2025

past it to chat gpt it will save your time and our time too.

danielfl

Aug 27, 2025

fair enough.

tried grok4 before asking, but gpt5 really found out which flags to use.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment