LLM EXPLORER 60,384 MODELS INDEXED

Soar Qwen 7B by julien31

By julien31 · 52 downloads
HF Repo ↗ Copy URL

Soar Qwen 7B is an open-source language model by julien31. Features: 7b LLM, VRAM: 15.2GB, Context: 32K, License: apache-2.0, Instruction-Based, Code Generating, LLM Explorer Score: 0.19.

  Arxiv:2507.14172   Arc   Arc-agi Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-coder-...   Code-generation   Codegen   Conversational Dataset:julien31/soar arc trai...   Endpoints compatible   Evolutionary-algorithms   Instruct   Qwen2   Region:us   Safetensors   Sharded   Soar   Tensorflow
Model Card on HF 🤗: https://huggingface.co/julien31/Soar-qwen-7b 

Soar Qwen 7B Parameters and Internals

LLM NameSoar Qwen 7B
Repository 🤗https://huggingface.co/julien31/Soar-qwen-7b 
Base Model(s)  Qwen/Qwen2.5-Coder-7B-Instruct   Qwen/Qwen2.5-Coder-7B-Instruct
Model Size7b
Required VRAM15.2 GB
Updated2026-08-08
Maintainerjulien31
Model Typeqwen2
Instruction-BasedYes
Model Files  4.9 GB: 1-of-4   4.9 GB: 2-of-4   4.3 GB: 3-of-4   1.1 GB: 4-of-4
Generates CodeYes
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.49.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|PAD_TOKEN|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Soar Qwen 7B

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 7B Rebase986K / 15.2 GB732
Qwen2.5 7B Rebase986K / 15.2 GB132
StockQwen 2.5 7B128K / 15.2 GB696
DareQwen 2.5 7B128K / 15.2 GB111
Tessa T1 7B117K / 15.2 GB1410
UIGEN T1.5 7B117K / 15.2 GB126
Qwen2.5 Coder 7B Instruct32K / 15.2 GB2019400765
...Sft Reasoning Official Full Ft32K / 15.2 GB4640
Vibe Coder 7B Max32K / 15.3 GB4601
Finsec Detector32K / 15.2 GB3901
Note: green Score (e.g. "73.2") means that the model is better than julien31/Soar-qwen-7b.