LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Qwen3 4B 2509 1200step by fireworks1231

 »  All LLMs  »  fireworks1231  »  Qwen3 4B 2509 1200step   URL Share it on

  5   
  Autotrain compatible Base model:finetune:unsloth/qw... Base model:unsloth/qwen3-4b-th...   Conversational   En   Endpoints compatible   Qwen3   Region:us   Safetensors   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/fireworks1231/qwen3-4b-2509-1200step 

Qwen3 4B 2509 1200step Benchmarks

LLME Score: 0.26197
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3 4B 2509 1200step (fireworks1231/qwen3-4b-2509-1200step)
🌟 Advertise your project 🚀

Qwen3 4B 2509 1200step Parameters and Internals

LLM NameQwen3 4B 2509 1200step
Repository 🤗https://huggingface.co/fireworks1231/qwen3-4b-2509-1200step 
Base Model(s)  Qwen3 4B Thinking 2507   unsloth/Qwen3-4B-Thinking-2507
Model Size4b
Required VRAM8.1 GB
Updated2025-09-08
Maintainerfireworks1231
Model Typeqwen3
Model Files  5.0 GB: 1-of-2   3.1 GB: 2-of-2
Supported Languagesen
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version4.56.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Vocabulary Size151936
Errorsreplace

Best Alternatives to Qwen3 4B 2509 1200step

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 4B Instruct 2507256K / 8.1 GB946812270
Qwen3 4B Thinking 2507256K / 8.1 GB211950351
Jan V1 4B256K / 8.1 GB12628327
WEBGEN 4B Preview256K / 8.1 GB61655
Qwen3 4B Thinking 2507 FP8256K / 5.2 GB17761428
Qwen3 4B Instruct 2507 FP8256K / 5.2 GB2894727
Qwen3 4B Instruct 2507256K / 8.1 GB369788
...4B Thinking 2507 DAG Reasoning256K / 16.1 GB92634
Qwen3 4B Thinking 2507256K / 8.1 GB74384
P4 V1256K / 8.1 GB8860
Note: green Score (e.g. "73.2") means that the model is better than fireworks1231/qwen3-4b-2509-1200step.

Rank the Qwen3 4B 2509 1200step Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 51191 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124
  Support LLM Explorer