LLM EXPLORER 58,178 MODELS INDEXED

Qwen3 30B A3B FP8 by Qwen

By Qwen · 514204 downloads
HF Repo ↗ Copy URL

Qwen3 30B A3B FP8 is an open-source language model by Qwen. Features: 30b LLM, VRAM: 32.5GB, Context: 40K, License: apache-2.0, LLM Explorer Score: 0.28.

  Arxiv:2309.00071   Arxiv:2505.09388 Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3-30b-a3b   Endpoints compatible   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen3-30B-A3B-FP8 

Qwen3 30B A3B FP8 Parameters and Internals

LLM NameQwen3 30B A3B FP8
Repository 🤗https://huggingface.co/Qwen/Qwen3-30B-A3B-FP8 
Base Model(s)  Qwen3 30B A3B   Qwen/Qwen3-30B-A3B
Model Size30b
Required VRAM32.5 GB
Updated2026-07-01
MaintainerQwen
Model Typeqwen3_moe
Model Files  5.0 GB: 1-of-7   5.0 GB: 2-of-7   5.0 GB: 3-of-7   5.0 GB: 4-of-7   5.0 GB: 5-of-7   5.0 GB: 6-of-7   2.5 GB: 7-of-7
Model ArchitectureQwen3MoeForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.51.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen3 30B A3B FP8

Best Alternatives
Context / RAM
Downloads
Likes
...LL MASTER CODER M 1million Ctx1024K / 84.8 GB1209
... 42B A3B Thinking Total Recall986K / 84.8 GB260
Qwen3 30B A3B YOYO V3986K / 61.1 GB117
...07 YOYO2 TOTAL RECALL Instruct986K / 84.8 GB271
...07 YOYO2 TOTAL RECALL Instruct986K / 106 GB200
Qwen3 30B A3B YOYO V2986K / 61.1 GB194
Qwen3 Coder 30B A3B Instruct256K / 61.1 GB17467711168
Qwen3 30B A3B Instruct 2507256K / 61.1 GB393713
Qwen3 30B A3B Instruct 2507256K / 61.1 GB1903736824
...en3 Coder 30B A3B Instruct FP8256K / 31.2 GB1556690191
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen3-30B-A3B-FP8.