---

license: apache-2.0 pipeline_tag: text-generation library_name: node-llama-cpp tags:

• node-llama-cpp
• llama.cpp
• conversational

base_model: ByteDance-Seed/Seed-OSS-36B-Instruct quantized_by: giladgd

---

Seed-OSS-36B-Instruct-GGUF

Static quants of ByteDance-Seed/Seed-OSS-36B-Instruct.

Quants

Link	URI	Quant	Size
GGUF	hf:giladgd/Seed-OSS-36B-Instruct-GGUF:Q2K	Q2K	13.6GB
GGUF	hf:giladgd/Seed-OSS-36B-Instruct-GGUF:Q3KS	Q3K_S	15.9GB
GGUF	hf:giladgd/Seed-OSS-36B-Instruct-GGUF:Q3KM	Q3K_M	17.6GB
GGUF	hf:giladgd/Seed-OSS-36B-Instruct-GGUF:Q3KL	Q3K_L	19.1GB
GGUF	hf:giladgd/Seed-OSS-36B-Instruct-GGUF:Q40	Q40	20.6GB
GGUF	hf:giladgd/Seed-OSS-36B-Instruct-GGUF:Q4KS	Q4K_S	20.7GB
GGUF	hf:giladgd/Seed-OSS-36B-Instruct-GGUF:Q4KM	Q4K_M	21.8GB
GGUF	hf:giladgd/Seed-OSS-36B-Instruct-GGUF:Q50	Q50	25.0GB
GGUF	hf:giladgd/Seed-OSS-36B-Instruct-GGUF:Q5KS	Q5K_S	25.0GB
GGUF	hf:giladgd/Seed-OSS-36B-Instruct-GGUF:Q5KM	Q5K_M	25.6GB
GGUF	hf:giladgd/Seed-OSS-36B-Instruct-GGUF:Q6K	Q6K	29.7GB
GGUF	hf:giladgd/Seed-OSS-36B-Instruct-GGUF:Q80	Q80	38.4GB
GGUF	hf:giladgd/Seed-OSS-36B-Instruct-GGUF:F16	F16	72.3GB

[!TIP]

Download a quant using node-llama-cpp (more info):

> npx -y node-llama-cpp pull <URI>

>

Usage

Use with node-llama-cpp (recommended)

Ensure you have node.js installed:

brew install nodejs

CLI

Chat with the model:

npx -y node-llama-cpp chat hf:giladgd/Seed-OSS-36B-Instruct-GGUF:Q4KM

Code

Use it in your project:

npm install node-llama-cpp

import {getLlama, resolveModelFile, LlamaChatSession} from "node-llama-cpp";

const modelUri = "hf:giladgd/Seed-OSS-36B-Instruct-GGUF:Q4KM";

const llama = await getLlama();
const model = await llama.loadModel({
    modelPath: await resolveModelFile(modelUri)
});
const context = await model.createContext();
const session = new LlamaChatSession({
    contextSequence: context.getSequence()
});

const q1 = "Hi there, how are you?";
console.log("User: " + q1);

const a1 = await session.prompt(q1);
console.log("AI: " + a1);

[!TIP]

Read the getting started guide to quickly scaffold a new node-llama-cpp project

Use with llama.cpp

Install llama.cpp through brew (works on Mac and Linux)

brew install llama.cpp

CLI

llama-cli -hf giladgd/Seed-OSS-36B-Instruct-GGUF:Q4KM -p "The meaning to life and the universe is"

Server

llama-server -hf giladgd/Seed-OSS-36B-Instruct-GGUF:Q4KM -c 2048