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

This is the GGUF quantized version of ArliAI's GLM-4.5-Air-Derestricted model. It uses llama.cpp and imatrix technology for optimized quantization processing, offering multiple quantization levels to suit different hardware configurations and performance requirements.

Natural Language ProcessingGguf

This is an experimental quantized large language model that uses the Deckard (qx) quantization method with 3-bit quantization for the embedding layer. The model is reconstructed using the Norm-Preserving Bi-Projection Elimination (NPBA) technique, which not only removes the security restriction mechanism but also enhances the model's cognitive depth and reasoning ability.

Natural Language ProcessingMlx

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 large language model with 139B parameters obtained by uniformly pruning 40% of the experts in MiniMax-M2 using the REAP method. It adopts the GLM architecture and Mixture of Experts (MoE) technology, and undergoes various quantization processes through llama.cpp, suitable for text generation tasks.

Natural Language ProcessingGgufEnglish

GLM-4.6 AWQ - INT4 is a 4-bit quantized version of the GLM-4.6 model, using the AWQ quantization method. It significantly reduces the storage and computing resource requirements while maintaining the model's performance. This model supports a 200K context length and shows significant improvements in coding, reasoning, and agent tasks compared to GLM-4.5.

Natural Language ProcessingTransformersMultiple Languages

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 Q4_K_M gguf quantized version of the GLM-4.6-REAP-266B-A32B model, built on the transformers library, with text generation capabilities. The model uses the REAP (Routing-Weighted Expert Activation Pruning) method, which can selectively remove redundant experts while retaining the router's independent control over the remaining experts.

Natural Language ProcessingTransformers

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

This model is a mixture of experts model after 25% uniform pruning of GLM-4.5-Air using the REAP method. It has been converted to a 4-bit quantized version in the MLX format, suitable for efficient inference on Apple chip devices.

Natural Language ProcessingTransformersEnglish

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-4.5-Air-REAP-82B-A12B is an efficiently compressed version of GLM-4.5-Air. Through the REAP pruning technology, the parameter scale is compressed from 106B to 82B, reducing the memory requirement by 25% while maintaining nearly lossless performance.

Natural Language ProcessingTransformersEnglish

This project provides creative writing control vectors for the GLM-4.6 model. Through the control vector technology, the model's performance in specific dimensions can be adjusted, such as honesty and Machiavellianism tendencies, communication style, etc.

Natural Language ProcessingTransformersEnglish

This is an MLX format version converted from the GLM-4.6 model, using 8-bit quantization technology with a group size of 32, optimized for Apple chips, and providing efficient text generation capabilities.

Natural Language ProcessingMlxMultiple Languages

A high-quality quantized version of GLM-4.6, implemented using advanced quantization techniques without using imatrix, maintaining good model performance and compatibility, suitable for various application scenarios such as dialogue.

Natural Language ProcessingGguf

GLM-4.6-AWQ is a model that performs high-performance AWQ quantization on Zhipu AI's GLM-4.6 (357B MoE). It is optimized for vLLM inference and can effectively improve the throughput of production deployment. This model uses 4-bit quantization technology, which significantly reduces video memory usage while maintaining high accuracy.

Natural Language ProcessingTransformersMultiple Languages

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