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

Qwen3 30B A3B Instruct 2507 FP8 by unsloth

 »  All LLMs  »  unsloth  »  Qwen3 30B A3B Instruct 2507 FP8   URL Share it on

  23   
  Arxiv:2505.09388   Autotrain compatible Base model:quantized:qwen/qwen... Base model:qwen/qwen3-30b-a3b-...   Conversational   Endpoints compatible   Fp8   Instruct   Qwen3 moe   Region:us   Safetensors   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/Qwen3-30B-A3B-Instruct-2507-FP8 

Qwen3 30B A3B Instruct 2507 FP8 Benchmarks

LLME Score: 0.31207
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3 30B A3B Instruct 2507 FP8 (unsloth/Qwen3-30B-A3B-Instruct-2507-FP8)
🌟 Advertise your project 🚀

Qwen3 30B A3B Instruct 2507 FP8 Parameters and Internals

LLM NameQwen3 30B A3B Instruct 2507 FP8
Repository 🤗https://huggingface.co/unsloth/Qwen3-30B-A3B-Instruct-2507-FP8 
Base Model(s)  ...wen3 30B A3B Instruct 2507 FP8   Qwen/Qwen3-30B-A3B-Instruct-2507-FP8
Model Size30b
Required VRAM31.2 GB
Updated2025-07-31
Maintainerunsloth
Model Typeqwen3_moe
Instruction-BasedYes
Model Files  10.0 GB: 1-of-4   10.0 GB: 2-of-4   10.0 GB: 3-of-4   1.2 GB: 4-of-4
Model ArchitectureQwen3MoeForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version4.54.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen3 30B A3B Instruct 2507 FP8

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 30B A3B Instruct 2507256K / 61.1 GB1489259
...wen3 30B A3B Instruct 2507 FP8256K / 31.2 GB194743
Qwen3 30B A3B Instruct 2507256K / 61.1 GB874
...30B A3B Instruct 2507 MLX 4bit256K / 17.2 GB254655
...30B A3B Instruct 2507 MLX 8bit256K / 32.5 GB253232
...en3 30B A3B Instruct 2507 4bit256K / 61.2 GB722
Q3 30B A3B Designant32K / 61.1 GB2513
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Qwen3-30B-A3B-Instruct-2507-FP8.

Rank the Qwen3 30B A3B Instruct 2507 FP8 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? 50263 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