GLM 4.5 Int4 Mixed AutoRound by Intel

 ยป  All LLMs  ยป  Intel  ยป  GLM 4.5 Int4 Mixed AutoRound   URL Share it on

  Arxiv:2309.05516   4-bit   Auto-round Base model:quantized:zai-org/g...   Base model:zai-org/glm-4.5   Conversational   Glm4 moe   Region:us   Safetensors   Sharded   Tensorflow

GLM 4.5 Int4 Mixed AutoRound Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
GLM 4.5 Int4 Mixed AutoRound (Intel/GLM-4.5-int4-mixed-AutoRound)
๐ŸŒŸ Advertise your project ๐Ÿš€

GLM 4.5 Int4 Mixed AutoRound Parameters and Internals

LLM NameGLM 4.5 Int4 Mixed AutoRound
Repository ๐Ÿค—https://huggingface.co/Intel/GLM-4.5-int4-mixed-AutoRound 
Base Model(s)  zai-org/GLM-4.5   zai-org/GLM-4.5
Required VRAM192.4 GB
Updated2025-08-17
MaintainerIntel
Model Typeglm4_moe
Model Files  5.0 GB: 1-of-39   5.0 GB: 2-of-39   5.0 GB: 3-of-39   5.0 GB: 4-of-39   5.0 GB: 5-of-39   5.0 GB: 6-of-39   5.0 GB: 7-of-39   5.0 GB: 8-of-39   5.0 GB: 9-of-39   5.0 GB: 10-of-39   5.0 GB: 11-of-39   5.0 GB: 12-of-39   5.0 GB: 13-of-39   5.0 GB: 14-of-39   5.0 GB: 15-of-39   5.0 GB: 16-of-39   5.0 GB: 17-of-39   5.0 GB: 18-of-39   5.0 GB: 19-of-39   5.0 GB: 20-of-39   5.0 GB: 21-of-39   5.0 GB: 22-of-39   5.0 GB: 23-of-39   5.0 GB: 24-of-39   5.0 GB: 25-of-39   5.0 GB: 26-of-39   5.0 GB: 27-of-39   5.0 GB: 28-of-39   5.0 GB: 29-of-39   5.0 GB: 30-of-39   5.0 GB: 31-of-39   5.0 GB: 32-of-39   5.0 GB: 33-of-39   5.0 GB: 34-of-39   5.0 GB: 35-of-39   5.0 GB: 36-of-39   5.0 GB: 37-of-39   5.0 GB: 38-of-39   2.4 GB: 39-of-39
Model ArchitectureGlm4MoeForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.56.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|endoftext|>
Vocabulary Size151552
Torch Data Typebfloat16

Best Alternatives to GLM 4.5 Int4 Mixed AutoRound

Best Alternatives
Context / RAM
Downloads
Likes
GLM 4.5 AWQ128K / 194.2 GB9208
GLM 4.5 GPTQ Int4 Int8Mix128K / 203.9 GB8334
Note: green Score (e.g. "73.2") means that the model is better than Intel/GLM-4.5-int4-mixed-AutoRound.

Rank the GLM 4.5 Int4 Mixed AutoRound Capabilities

๐Ÿ†˜ Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! ๐ŸŒŸ

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 50728 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124