# Local deployment

Jan-nano-8bit is an 8-bit quantized version converted from the Menlo/Jan-nano model, optimized for the MLX framework and suitable for text generation tasks.

MiniCPM4-8B-Q8_0-GGUF is a model converted from openbmb/MiniCPM4-8B to GGUF format via llama.cpp, suitable for local inference.

Chinda LLM 4B is a cutting-edge Thai model launched by iApp Technology, built on the Qwen3-4B architecture, bringing advanced thinking capabilities to the Thai AI ecosystem.

Qwen3-235B-A22B-4bit-DWQ is a 4-bit quantized version converted from the Qwen3-235B-A22B-8bit model, suitable for text generation tasks.

Qwen3-8B-4bit-AWQ is a 4-bit AWQ quantized version converted from Qwen/Qwen3-8B, suitable for text generation tasks in the MLX framework.

The GGUF quantized version of Qwen3-30B-A3B, supporting multi-bit quantization, suitable for text generation tasks.

Qwen3-30B-A3B-4bit is a 4-bit quantized version converted from Qwen/Qwen3-30B-A3B, suitable for efficient text generation tasks under the MLX framework.

GGUF quantized version of Qwen3-0.6B, suitable for text generation tasks.

Qwen3-14B-4bit is a 4-bit quantized version of the Qwen/Qwen3-14B model converted using mlx-lm, suitable for text generation tasks.

OuteTTS is a text-to-speech (TTS) model focused on the Turkish language, based on a 500M parameter scale, capable of converting Turkish text into natural speech.

This is a 3B-parameter language model optimized for Korean, converted to GGUF format for compatibility with llama.cpp.

This is a GGUF format quantized version of the mrfakename/mistral-small-3.1-24b-instruct-2503-hf model, suitable for text generation tasks.

This is a GGUF format model converted from Google's Gemma 3.4B parameter model, suitable for text generation tasks.

This is a quantized version in GGUF format based on the Llama-3.1-8B-RainbowLight-EtherealMix model, which facilitates the development of applications related to text generation.

GGUF format quantized version of QwQ-32B, suitable for local text generation tasks.

This is a Thai female voice text-to-speech (TTS) model, fine-tuned based on the VITS architecture, supporting high-quality Thai speech synthesis.

Indri is a text-to-speech (TTS) model supporting English and Hindi, with a parameter size of 124M, optimized for CPU inference in GGUF format.

A large language model developed by Alibaba NLP team, based on the Qwen2 architecture with 7B parameters, supporting instruction interaction

MLX implementation of Stable Diffusion 3 Medium, focused on text-to-image generation

This is a 4-bit quantized 135M parameter small language model, suitable for text generation tasks in resource-constrained environments.

DeepSeek-V2-Lite-Chat is a lightweight chat model optimized based on the DeepSeek-V2 architecture, suitable for efficient dialogue generation tasks.

This is a GGUF format model converted from Google's Gemma 2B model, suitable for text generation tasks.

The GGUF quantized version of Qwen2-7B-Instruct, suitable for local deployment and inference

This is a Ukrainian and English language model based on the Llama-2-7b architecture, converted to GGUF format for use with the llama.cpp framework.

The GGUF quantized version of the Llama 3 8B instruction model, suitable for local inference and supporting efficient deployment

Gemma is a series of lightweight cutting-edge open-source large language models launched by Google, developed based on the Gemini technology framework, supporting English text generation tasks.

TinyLlama is a lightweight 1.1B-parameter Llama model optimized for chat and programming assistance tasks.

Pandora-v1-13B is a 13B-parameter large language model that integrates multiple 7B models, using the passthrough fusion method to combine the best-performing 7B models from the OpenLLM leaderboard.