LLM EXPLORER 65,121 MODELS INDEXED

Qwen35 4B Soyuz Merged by AlexWortega

By AlexWortega · 246 downloads
HF Repo ↗ Copy URL

Qwen35 4B Soyuz Merged is an open-source language model by AlexWortega. Features: 4b LLM, VRAM: 8.4GB, Context: 256K, License: apache-2.0, LLM Explorer Score: 0.24.

  Agent Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3.5-4b   Conversational   Dataset:alexwortega/soyuz-sft   En   Endpoints compatible   Hermes   Merge   Qwen3.5   Qwen3 5 text   Region:us   Sft   Soyuz
Model Card on HF 🤗: https://huggingface.co/AlexWortega/qwen35-4b-soyuz-merged 

Qwen35 4B Soyuz Merged Parameters and Internals

LLM NameQwen35 4B Soyuz Merged
Repository 🤗https://huggingface.co/AlexWortega/qwen35-4b-soyuz-merged 
Base Model(s)  Qwen/Qwen3.5-4B   Qwen/Qwen3.5-4B
Model Size4b
Required VRAM8.4 GB
Updated2026-10-21
MaintainerAlexWortega
Model Typeqwen3_5_text
Model Files  8.4 GB
Supported Languagesen
Model ArchitectureQwen3_5ForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version5.5.1
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Vocabulary Size248320
Errorsreplace

Best Alternatives to Qwen35 4B Soyuz Merged

Best Alternatives
Context / RAM
Downloads
Likes
Agents A1 4B Fable Preview256K / 8.4 GB1030
Decider 4B256K / 8.4 GB2356517
NeoHorse 1 4B256K / 8.4 GB1771179
JevK5256K / 8.4 GB552513
Plumb 4B256K / 8.4 GB28256
JSBAI Coder 4B256K / 8.4 GB27951
Aztec Coder 4B256K / 8.4 GB11974
Cisimcik 4B256K / 8.4 GB8481
Wald 4B256K / 8.4 GB7067
WikiQwen 4B256K / 8.4 GB11252
Note: green Score (e.g. "73.2") means that the model is better than AlexWortega/qwen35-4b-soyuz-merged.