LLM EXPLORER 61,491 MODELS INDEXED

Qwen3 Coder 30B A3B Instruct FP8 by Qwen

By Qwen · 1556690 downloads
HF Repo ↗ Copy URL

Qwen3 Coder 30B A3B Instruct FP8 is an open-source language model by Qwen. Features: 30b LLM, VRAM: 31.2GB, Context: 256K, License: apache-2.0, Instruction-Based, Code Generating, LLM Explorer Score: 0.32.

  Arxiv:2505.09388   Codegen   Conversational   Deploy:azure   Endpoints compatible   Fp8   Instruct   Qwen3 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8 

Qwen3 Coder 30B A3B Instruct FP8 Parameters and Internals

LLM NameQwen3 Coder 30B A3B Instruct FP8
Repository 🤗https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8 
Model Size30b
Required VRAM31.2 GB
Updated2026-07-16
MaintainerQwen
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
Generates CodeYes
Model ArchitectureQwen3MoeForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version4.52.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen3 Coder 30B A3B Instruct FP8

Best Alternatives
Context / RAM
Downloads
Likes
...LL MASTER CODER M 1million Ctx1024K / 84.8 GB19511
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
Tiny Pickle V3 Coder256K / 61.2 GB640
Qwen3 Coder 30B A3B Instruct256K / 61.1 GB903427
Qwen3 Coder REAP 25B A3B256K / 49.8 GB57988
Qwen3 30B A3B YOYO V6256K / 61.1 GB197
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8.