Qwen 1.5 4B Layer Mix Bpw 2.5 by GreenBitAI

 ยป  All LLMs  ยป  GreenBitAI  ยป  Qwen 1.5 4B Layer Mix Bpw 2.5   URL Share it on

  Autotrain compatible   Conversational   Endpoints compatible   Qwen2   Region:us   Safetensors

Qwen 1.5 4B Layer Mix Bpw 2.5 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
๐ŸŒŸ Advertise your project ๐Ÿš€

Qwen 1.5 4B Layer Mix Bpw 2.5 Parameters and Internals

Model Type 
low-bit, quantized
Additional Notes 
GreenBitAI's pretrained low-bit LLMs with extreme compression yet still strong performance.
LLM NameQwen 1.5 4B Layer Mix Bpw 2.5
Repository ๐Ÿค—https://huggingface.co/GreenBitAI/Qwen-1.5-4B-layer-mix-bpw-2.5 
Model Size4b
Required VRAM2.7 GB
Updated2025-06-09
MaintainerGreenBitAI
Model Typeqwen2
Model Files  2.7 GB
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.39.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typefloat16
Errorsreplace
Qwen 1.5 4B Layer Mix Bpw 2.5 (GreenBitAI/Qwen-1.5-4B-layer-mix-bpw-2.5)

Best Alternatives to Qwen 1.5 4B Layer Mix Bpw 2.5

Best Alternatives
Context / RAM
Downloads
Likes
Qwarkstar 4B Instruct Preview32K / 9 GB172
Qwen1.5 4B Chat32K / 7.9 GB1247841
Qwarkstar 4B32K / 9 GB80
Qwen1.5 4B32K / 7.9 GB1711436
Qwarkstar 4B Instruct32K / 9 GB301
Sailor 4B32K / 7.9 GB196
Nusantara 4B Indo Chat32K / 7.9 GB141
Sailor 4B Chat32K / 7.9 GB182
Reyna CoT 4B V0.132K / 7.9 GB186
Blossom V5 4B32K / 7.9 GB162
Note: green Score (e.g. "73.2") means that the model is better than GreenBitAI/Qwen-1.5-4B-layer-mix-bpw-2.5.

Rank the Qwen 1.5 4B Layer Mix Bpw 2.5 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? 48023 in total.

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