LLM EXPLORER 58,744 MODELS INDEXED

Qwen3 30B A3B FP4 by nvidia

By nvidia · 1201 downloads
HF Repo ↗ Copy URL

Qwen3 30B A3B FP4 is an open-source language model by nvidia. Features: 30b LLM, VRAM: 20.7GB, Context: 40K, License: apache-2.0, LLM Explorer Score: 0.21.

  8-bit Base model:quantized:qwen/qwen...   Base model:qwen/qwen3-30b-a3b   Conversational   Fp4   Model optimizer   Modelopt   Nvidia   Quantized   Qwen3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/nvidia/Qwen3-30B-A3B-FP4 

Qwen3 30B A3B FP4 Parameters and Internals

LLM NameQwen3 30B A3B FP4
Repository 🤗https://huggingface.co/nvidia/Qwen3-30B-A3B-FP4 
Base Model(s)  Qwen3 30B A3B   Qwen/Qwen3-30B-A3B
Model Size30b
Required VRAM20.7 GB
Updated2025-09-10
Maintainernvidia
Model Typeqwen3
Model Files  5.0 GB: 1-of-5   4.9 GB: 2-of-5   4.9 GB: 3-of-5   4.3 GB: 4-of-5   1.6 GB: 5-of-5
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.51.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen3 30B A3B FP4

Best Alternatives
Context / RAM
Downloads
Likes
...4b Onpolicy 5k Src30k 35k Cont256K / 17.6 GB4300
...licy 5k Src20k 25k Freeze Rock256K / 8.9 GB80
...n3 30b A3b To 4b Offpolicy 20k256K / 17.6 GB90
Note: green Score (e.g. "73.2") means that the model is better than nvidia/Qwen3-30B-A3B-FP4.