LLM EXPLORER 60,645 MODELS INDEXED

Qwen2.5 7B Preview by marcuscedricridia

By marcuscedricridia · 10 downloads
HF Repo ↗ Copy URL

Qwen2.5 7B Preview is an open-source language model by marcuscedricridia. Features: 7b LLM, VRAM: 15.2GB, Context: 986K, Merged, LLM Explorer Score: 0.41, ELO: 1435.

  Merged Model   Arxiv:2406.11617 Base model:marcuscedricridia/a... Base model:marcuscedricridia/q... Base model:marcuscedricridia/s...   Conversational   Endpoints compatible   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/marcuscedricridia/Qwen2.5-7B-Preview 

Qwen2.5 7B Preview Benchmarks

LMSys ELO 1435 vs 1272 (so35) 12.8%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Qwen2.5 7B Preview Parameters and Internals

LLM NameQwen2.5 7B Preview
Repository 🤗https://huggingface.co/marcuscedricridia/Qwen2.5-7B-Preview 
Base Model(s)  marcuscedricridia/Qwen2.5-7B-1M   Sbr O1 7B   Absolute O1 7B   marcuscedricridia/Qwen2.5-7B-1M   marcuscedricridia/sbr-o1-7b   marcuscedricridia/absolute-o1-7b
Merged ModelYes
Model Size7b
Required VRAM15.2 GB
Updated2026-05-18
Maintainermarcuscedricridia
Model Typeqwen2
Model Files  5.0 GB: 1-of-4   4.9 GB: 2-of-4   5.0 GB: 3-of-4   0.3 GB: 4-of-4
Model ArchitectureQwen2ForCausalLM
Context Length1010000
Model Max Length1010000
Transformers Version4.49.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151665
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen2.5 7B Preview

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 7B Instruct 1M986K / 15.4 GB52534373
Rewnozom986K / 30.5 GB7421
Hush Qwen2.5 7B V1.2986K / 15.2 GB41
Hush Qwen2.5 7B V1.1986K / 15.2 GB51
Hush Qwen2.5 7B V1.4986K / 15.2 GB81
Hush Qwen2.5 7B Preview986K / 15.2 GB50
Hush Qwen2.5 7B V1.3986K / 15.2 GB102
Hush Qwen2.5 7B RP V1.4 1M986K / 15.2 GB102
Qwen 2.5 7B Exp Sce986K / 15.2 GB102
Qwen2.5 7B MixStock V0.1986K / 15.2 GB63