LLM EXPLORER 68,192 MODELS INDEXED

Qwen3 4B Toolcall DPO Merged by arman-52

By arman-52 · 70 downloads

Qwen3 4B Toolcall DPO Merged is an open-source language model by arman-52. Features: 4b LLM, VRAM: 8GB, Context: 256K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.29.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-4b-instr...   Conversational   Dpo   En   Endpoints compatible   Function-calling   Instruct   Json-schema   Qlora   Qwen3   Region:us   Safetensors   Sft   Structured-output   Tool-calling   Trl

Qwen3 4B Toolcall DPO Merged Parameters and Internals

LLM NameQwen3 4B Toolcall DPO Merged
Repository πŸ€—https://huggingface.co/arman-52/qwen3-4b-toolcall-dpo-merged 
Base Model(s)  Qwen3 4B Instruct 2507   Qwen/Qwen3-4B-Instruct-2507
Model Size4b
Required VRAM8 GB
Updated2026-11-21
Maintainerarman-52
Model Typeqwen3
Instruction-BasedYes
Model Files  8.0 GB
Supported Languagesen
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version5.23.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Errorsreplace

Best Alternatives to Qwen3 4B Toolcall DPO Merged

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 4B Instruct 2507256K / 8.1 GB3109972911
Oc E Non V1256K / 8 GB94721
FastContext 1.0 4B SFT256K / 8.1 GB5735357
Carenudge Qwen3 4B256K / 8 GB5761
Qwen3 4B Instruct 2507 FP8256K / 5.2 GB110074478
SRA RiskGate 4B256K / 8 GB26621
FastContext 1.0 4B RL256K / 8.1 GB455961
...orm3200 Impl Verl S11 Step 039256K / 8.1 GB6451
Dwight 4B256K / 8.1 GB37410
Kanso Satori 1.0 Bf16256K / 8 GB4080
Note: green Score (e.g. "73.2") means that the model is better than arman-52/qwen3-4b-toolcall-dpo-merged.