Instructions to use drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-GGUF", dtype="auto")

llama-cpp-python

How to use drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-GGUF",
	filename="seed-oss-36b-base-wosyn-q4_k_m.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-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 drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-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 drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-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 drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-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 drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-GGUF:Q4_K_M

Use Docker

docker model run hf.co/drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-GGUF:Q4_K_M

SGLang

How to use drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-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 "drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-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": "drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-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 "drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-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": "drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-GGUF with Ollama:
```
ollama run hf.co/drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-GGUF:Q4_K_M
```

Unsloth Studio

How to use drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-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 drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-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 drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-GGUF with Docker Model Runner:
```
docker model run hf.co/drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-GGUF:Q4_K_M
```

Lemonade

How to use drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull drmcbride/Seed-OSS-36B-Base-woSyn-Q4_K_M-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Seed-OSS-36B-Base-woSyn-Q4_K_M-GGUF-Q4_K_M

List all available models

lemonade list

Error when using this in ollama

by mahmoudimus - opened Aug 25, 2025

Discussion

mahmoudimus

Aug 25, 2025

llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv   0:                       general.architecture str              = seed_oss
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Seed OSS 36B Base woSyn
llama_model_loader: - kv   3:                           general.finetune str              = Base-woSyn
llama_model_loader: - kv   4:                           general.basename str              = Seed-OSS
llama_model_loader: - kv   5:                         general.size_label str              = 36B
llama_model_loader: - kv   6:                            general.license str              = apache-2.0
llama_model_loader: - kv   7:                               general.tags arr[str,2]       = ["vllm", "text-generation"]
llama_model_loader: - kv   8:                       seed_oss.block_count u32              = 64
llama_model_loader: - kv   9:                    seed_oss.context_length u32              = 524288
llama_model_loader: - kv  10:                  seed_oss.embedding_length u32              = 5120
llama_model_loader: - kv  11:               seed_oss.feed_forward_length u32              = 27648
llama_model_loader: - kv  12:              seed_oss.attention.head_count u32              = 80
llama_model_loader: - kv  13:           seed_oss.attention.head_count_kv u32              = 8
llama_model_loader: - kv  14:                    seed_oss.rope.freq_base f32              = 10000000.000000
llama_model_loader: - kv  15:  seed_oss.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  16:              seed_oss.attention.key_length u32              = 128
llama_model_loader: - kv  17:            seed_oss.attention.value_length u32              = 128
llama_model_loader: - kv  18:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  19:                         tokenizer.ggml.pre str              = seed-coder
llama_model_loader: - kv  20:                      tokenizer.ggml.tokens arr[str,155136]  = ["<seed:bos>", "<seed:pad>", "<seed:e...
llama_model_loader: - kv  21:                  tokenizer.ggml.token_type arr[i32,155136]  = [3, 3, 3, 4, 4, 4, 4, 4, 4, 3, 3, 3, ...
llama_model_loader: - kv  22:                      tokenizer.ggml.merges arr[str,154737]  = ["Ġ Ġ", "Ġ t", "i n", "Ġ a", "e r...
llama_model_loader: - kv  23:                tokenizer.ggml.bos_token_id u32              = 0
llama_model_loader: - kv  24:                tokenizer.ggml.eos_token_id u32              = 2
llama_model_loader: - kv  25:            tokenizer.ggml.padding_token_id u32              = 1
llama_model_loader: - kv  26:               general.quantization_version u32              = 2
llama_model_loader: - kv  27:                          general.file_type u32              = 15
llama_model_loader: - type  f32:  321 tensors
llama_model_loader: - type q4_K:  385 tensors
llama_model_loader: - type q6_K:   65 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q4_K - Medium
print_info: file size   = 20.26 GiB (4.81 BPW) 
llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'seed_oss'

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