Run any LLM locally.
Use it from any language.
Deploy anywhere.

use mullama::{Model, Context, ContextParams};

let model = Model::load("llama3.2-1b.gguf")?;
let mut ctx = Context::new(&model, ContextParams::default())?;
let response = ctx.generate("Hello, AI!", 256)?;
println!("{response}");

from mullama import Model, Context

model = Model.load("llama3.2-1b.gguf", n_gpu_layers=32)
ctx = Context(model, n_ctx=4096)
print(ctx.generate("Hello, AI!"))

const { Model, Context } = require("mullama");

const model = Model.load("llama3.2-1b.gguf", { nGpuLayers: 32 });
const ctx = new Context(model, { nCtx: 4096 });
console.log(ctx.generate("Hello, AI!"));

import "github.com/cognisoc/mullama"

model, _ := mullama.LoadModel("llama3.2-1b.gguf", &mullama.ModelParams{NGpuLayers: 32})
ctx, _   := mullama.NewContext(model, &mullama.ContextParams{NCtx: 4096})
response, _ := ctx.Generate("Hello, AI!", 256, nil)

use Mullama\Model;
use Mullama\Context;

$model = Model::load("llama3.2-1b.gguf", ["nGpuLayers" => 32]);
$ctx   = new Context($model, ["nCtx" => 4096]);
echo $ctx->generate("Hello, AI!");

#include "mullama.h"

mullama_model* model = mullama_load_model("llama3.2-1b.gguf", NULL);
mullama_ctx*   ctx   = mullama_new_context(model, NULL);
char buf[2048];
mullama_generate(ctx, "Hello, AI!", buf, sizeof(buf));
puts(buf);