# 8B Parameters

This is a large language model converted based on the MLX format, suitable for text generation tasks.

Kanana-1.5-8B-Instruct-2505 is an 8B-parameter instruction fine-tuned language model developed by Kakao Corp, suitable for text generation tasks.

marin-8b-instruct is an 8B-parameter-scale instruction fine-tuned language model suitable for text generation tasks.

Qwen3-8B-bf16 is an MLX format model converted from Qwen/Qwen3-8B, supporting text generation tasks.

The Flex.1 alpha 8B model is a text-to-image generation model converted to GGUF format, specifically designed for the ComfyUI-GGUF tool.

Flux.1-lite-8B-alpha is a text-to-image generation model capable of converting textual descriptions into images.

Llama-3-Chinese-8B-Instruct-v3 is a Chinese instruction model fine-tuned from multiple hybrid models, suitable for dialogue, Q&A, and similar scenarios.

A large language model for the medical domain developed by John Snow Labs, based on supervised fine-tuning (SFT) of Meta-Llama-3-8B