LLM EXPLORER 58,873 MODELS INDEXED

Qwen2.5 8x7B Vee Eight Coder Instruct 53B by DavidAU

By DavidAU · 7 downloads
HF Repo ↗ Copy URL

Qwen2.5 8x7B Vee Eight Coder Instruct 53B is an open-source language model by DavidAU. Features: 53.2b LLM, VRAM: 107.3GB, Context: 32K, License: apache-2.0, MoE, Instruction-Based, Code Generating, LLM Explorer Score: 0.19.

  8x7b   Autotrain compatible Base model:julien31/soar-qwen-... Base model:merge:julien31/soar... Base model:merge:open-r1/olymp... Base model:merge:qwen/qwen2.5-... Base model:merge:snowflake/arc... Base model:merge:tesslate/tess... Base model:merge:tiger-lab/vis... Base model:merge:westenfelder/... Base model:merge:zhuyaoyu/code... Base model:open-r1/olympiccode... Base model:qwen/qwen2.5-coder-... Base model:snowflake/arctic-te... Base model:tesslate/tessa-rust... Base model:tiger-lab/viscoder-... Base model:westenfelder/qwen2.... Base model:zhuyaoyu/codev-r1-q...   Chat   Code   Code generation   Codegen   Codeqwen   Coder   Coding   Conversational   En   Endpoints compatible   Instruct   Merge   Mixture of experts   Moe   Qwen   Qwen-coder   Qwen2   Qwen2 moe   Qwen2moe   Region:us   Safetensors   Sharded   Shared expert   Tensorflow
Model Card on HF 🤗: https://huggingface.co/DavidAU/Qwen2.5-8x7B-Vee-Eight-Coder-Instruct-53B 

Qwen2.5 8x7B Vee Eight Coder Instruct 53B Parameters and Internals

LLM NameQwen2.5 8x7B Vee Eight Coder Instruct 53B
Repository 🤗https://huggingface.co/DavidAU/Qwen2.5-8x7B-Vee-Eight-Coder-Instruct-53B 
Base Model(s)  OlympicCoder 7B   Qwen/Qwen2.5-Coder-7B-Instruct   CodeV R1 Qwen 7B   VisCoder 7B   Soar Qwen 7B   Tessa Rust T1 7B   Arctic Text2SQL R1 7B   westenfelder/Qwen2.5-Coder-7B-Instruct-NL2SH   open-r1/OlympicCoder-7B   Qwen/Qwen2.5-Coder-7B-Instruct   zhuyaoyu/CodeV-R1-Qwen-7B   TIGER-Lab/VisCoder-7B   julien31/Soar-qwen-7b   Tesslate/Tessa-Rust-T1-7B   Snowflake/Arctic-Text2SQL-R1-7B   westenfelder/Qwen2.5-Coder-7B-Instruct-NL2SH
Model Size53.2b
Required VRAM107.3 GB
Updated2025-09-23
MaintainerDavidAU
Model Typeqwen2_moe
Instruction-BasedYes
Model Files  5.0 GB: 1-of-22   5.0 GB: 2-of-22   5.0 GB: 3-of-22   4.9 GB: 4-of-22   5.0 GB: 5-of-22   5.0 GB: 6-of-22   5.0 GB: 7-of-22   5.0 GB: 8-of-22   5.0 GB: 9-of-22   5.0 GB: 10-of-22   5.0 GB: 11-of-22   5.0 GB: 12-of-22   5.0 GB: 13-of-22   5.0 GB: 14-of-22   5.0 GB: 15-of-22   5.0 GB: 16-of-22   5.0 GB: 17-of-22   5.0 GB: 18-of-22   5.0 GB: 19-of-22   5.0 GB: 20-of-22   5.0 GB: 21-of-22   2.4 GB: 22-of-22
Supported Languagesen
Generates CodeYes
Model ArchitectureQwen2MoeForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.52.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|im_end|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace