INTELLECT-3 is a Mixture of Experts (MoE) inference model developed by Prime Intellect with a parameter scale of 106B (12B active parameters). It is supervised and fine-tuned based on GLM-4.5-Air-Base and trained through large-scale reinforcement learning, showing excellent performance in mathematics, coding, and inference tasks.

Natural Language ProcessingGguf

GLM-4.5-Air-REAP-82B-A12B-mxfp4-mlx is a large language model with 82B parameters compressed by the REAP method based on the GLM-4.5-Air model. It uses the MXFP4 quantization format and is optimized for Mac devices, significantly reducing memory usage while maintaining the performance of core tasks.

Natural Language ProcessingMlxEnglish

GLM-4.5-Iceblink-v2-106B-A12B-FP8 is a version based on the GLM-4.5-Iceblink-v2-106B-A12B model, using the most advanced mixture of experts quantization method for FP8 quantization. This model is specifically optimized for Ada, Hopper, or Blackwell series GPUs that support hardware FP8, significantly improving inference efficiency while maintaining high-quality output.

Natural Language ProcessingSafetensors

This is a mixture-of-experts model based on the GLM-4.6 architecture. The REAP method was used to uniformly prune 40% of the experts. The model has 218B parameters and has been converted to a 3-bit quantization version in the MLX format, which is suitable for efficient operation on Apple chip devices.

Natural Language ProcessingTransformersEnglish

This is the MXFP4_MOE quantized version of the GLM-4.5-Air-REAP-82B-A12B model, specifically optimized for text generation tasks. This model is based on the GLM-4.5-Air-REAP-82B-A12B base model of Cerebras and is implemented through MXFP4 mixed expert quantization technology, significantly reducing the model size and inference cost while maintaining performance.

Natural Language ProcessingGguf

This is the Q2_K_M gguf quantized version of the GLM-4.6-REAP-266B-A32B model, created based on the REAP (Router Weighted Expert Activation Pruning) method. It can selectively remove redundant experts while retaining the router's independent control over the remaining experts, achieving efficient text generation.

Natural Language ProcessingTransformers

Zirel-3 is a specific fine-tuned model based on GLM-4.5-Air-REAP-82B-A12B. It is an 82-billion-parameter mixture-of-experts model compressed using the REAP (Routing Weighted Expert Activation Pruning) technology, significantly reducing the model size while maintaining high performance.

Natural Language ProcessingTransformersEnglish

An optimized version based on the GLM-4.5-Air model with 25% expert pruning using the REAP method, converted to the MLX format for efficient operation on Apple Silicon devices

Natural Language ProcessingMlxEnglish

GLM-4.6-GPTQ-Int4-Int8Mix is a quantized version based on the zai-org/GLM-4.6 base model, which performs excellently in text generation tasks. This model achieves optimization of the model size through GPTQ quantization technology while maintaining good performance.

Natural Language ProcessingTransformers

This project provides a quantized version of zai-org/GLM-4.6, aiming to make knowledge accessible to everyone. It is a text generation model optimized based on the original GLM-4.6 model, offering more efficient inference performance.

Natural Language ProcessingGguf

GLM-4.6-AWQ is a quantized version based on the zai-org/GLM-4.6 base model, with efficient text generation capabilities. Compared with GLM-4.5, this model has significant improvements in aspects such as context window, encoding performance, reasoning ability, and agent functions.

Natural Language ProcessingTransformers

GLM-4.6 is an efficient text generation model based on the MLX framework. It uses 6.5-bit quantization technology, significantly reducing the computational resource requirements while maintaining high-quality text generation capabilities. This model can run on a single M3 Ultra device and supports efficient text generation tasks.

Natural Language ProcessingMlxMultiple Languages

This is a large language model with 9B parameters based on the GLM architecture, specifically optimized for reasoning tasks. It uses the GGUF format for easy deployment and use in llama.cpp. The model has been processed to eliminate censorship and has an uncensored feature.

Natural Language ProcessingTransformersMultiple Languages

This is a text generation model based on GLM-4.5-Air, specifically optimized with mxfp4 quantization for the MLX framework. The model provides a performance comparison analysis of multiple quantization versions (mxfp4, qx64, and qx5-hi), providing a basis for model selection in different task scenarios.

Natural Language ProcessingMlxMultiple Languages

GLM-4.5-Base is a text generation model that has undergone quantization processing. It is optimized based on the zai-org/GLM-4.5-Base model and is specifically designed for devices with 128GB of memory and a small GPU. It uses the new IQ2_KL quantization method of ik_llama.cpp, significantly reducing resource requirements while maintaining performance, and is suitable for text generation tasks.

Natural Language ProcessingGgufMultiple Languages

GLM-4.5-Air-AWQ is an 8-bit quantized version based on the GLM-4.5-Air base model, designed specifically for intelligent agents. It uses a hybrid reasoning mode, supports complex reasoning and instant response, and is released under the MIT open-source license.

Natural Language ProcessingTransformersMultiple Languages

GLM-4.5-AWQ is a 4-bit quantized version based on the GLM-4.5 base model. It uses the advanced AWQ quantization method, significantly improving inference efficiency while maintaining good performance. This model is specifically designed for intelligent agents, integrating reasoning, encoding, and intelligent agent capabilities.

Natural Language ProcessingTransformersMultiple Languages

A 2-bit quantized version converted from zai-org/GLM-4.5-Air based on mlx-lm 0.26.2. It is an efficient language model optimized for Apple Silicon, supporting Chinese and English text generation tasks.

Natural Language ProcessingMlxMultiple Languages

This is an experimental quantization version of the GLM-4.5-Air model based on ik_llama.cpp, optimized using imatrix technology. It is currently in the testing phase and is not suitable for wide use. This version achieves higher inference efficiency through advanced quantization technology, significantly reducing memory usage while maintaining model performance.

Natural Language ProcessingGguf

GLM-4.5-Air-AWQ is a text generation model that performs 4-bit AWQ quantization based on the zai-org/GLM-4.5-Air base model. It is specifically designed for intelligent agent applications and performs excellently in reasoning, coding, and intelligent agent capabilities. It uses the MIT open-source license.

Natural Language ProcessingTransformersMultiple Languages