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: 0.22.
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 Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Qwen3 30B A3B FP4 Parameters and Internals
| LLM Name | Qwen3 30B A3B FP4 |
| Repository 🤗 | https://huggingface.co/nvidia/Qwen3-30B-A3B-FP4 |
| Base Model(s) | |
| Model Size | 30b |
| Required VRAM | 20.7 GB |
| Updated | 2025-09-10 |
| Maintainer | nvidia |
| Model Type | qwen3 |
| Model Files | |
| Model Architecture | Qwen3ForCausalLM |
| License | apache-2.0 |
| Context Length | 40960 |
| Model Max Length | 40960 |
| Transformers Version | 4.51.3 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Qwen3 30B A3B FP4
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...n3 30b A3b To 4b Offpolicy 20k | 256K / 17.6 GB | 136 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than nvidia/Qwen3-30B-A3B-FP4 .
Rank the Qwen3 30B A3B FP4 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! 🌟
What open-source LLMs or SLMs are you in search of? 53444 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a