# Edge device inference

Dans-PersonalityEngine-V1.3.0-24b is a multi-functional model series that has been fine-tuned on more than 50 professional datasets and supports multilingual and professional domain tasks.

Quantized version of Qwen3-8B, utilizing IQ-DynamicGate ultra-low bit quantization technology to optimize memory efficiency and inference speed

Qwen2.5-7B-Instruct is an instruction-tuned model based on Qwen2.5-7B, optimized for text generation tasks, especially in chat scenarios.

Ultra-low-bit quantization (1-2 bit) model using IQ-DynamicGate technology, suitable for memory-constrained devices and efficient inference scenarios

GLM-Z1-32B-0414 is a 32B-parameter multilingual text generation model supporting Chinese and English, released under the MIT license.

Ultra-low-bit quantization (1-2 bits) model using IQ-DynamicGate technology, suitable for memory-constrained devices and edge computing scenarios

An instruction-tuned model based on OLMo-2-0325-32B-DPO, utilizing IQ-DynamicGate ultra-low bit quantization technology, optimized for memory-constrained environments.

IBM Granite series 8B parameter instruction-tuned language model, employing IQ-DynamicGate ultra-low-bit quantization technology, suitable for efficient inference scenarios

Mistral-7B-Instruct-v0.1 is a fine-tuned model based on Mistral-7B-v0.1, supporting text generation tasks. It employs IQ-DynamicGate ultra-low bit quantization technology, making it suitable for memory-constrained deployment environments.