What are the hardware requirements for Qwen3 Coder 30B A3B Instruct FP4?

Qwen3 Coder 30B A3B Instruct FP4 requires approximately 18.1 GB of VRAM and supports a context window of 256K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3 Coder 30B A3B Instruct FP4 and how large is it?

Qwen3 Coder 30B A3B Instruct FP4 is developed by NVFP4, a model with 30b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Qwen3 Coder 30B A3B Instruct FP4?

Qwen3 Coder 30B A3B Instruct FP4 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3 Coder 30B A3B Instruct FP4 by NVFP4 — VRAM 18.1GB, 256K context

Name: Qwen3 Coder 30B A3B Instruct FP4
Author: NVFP4

Qwen3 Coder 30B A3B Instruct FP4 is an open-source language model by NVFP4. Features: 30b LLM, VRAM: 18.1GB, Context: 256K, License: apache-2.0, Instruction-Based, Code Generating.

Arxiv:2505.09388 8-bit Base model:quantized:qwen/qwen... Base model:qwen/qwen3-coder-30... Codegen Conversational Fp4 Instruct Model optimizer Modelopt Nvidia Quantized Qwen3 Qwen3 moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/NVFP4/Qwen3-Coder-30B-A3B-Instruct-FP4

Qwen3 Coder 30B A3B Instruct FP4 Parameters and Internals

LLM Name	Qwen3 Coder 30B A3B Instruct FP4
Repository 🤗	https://huggingface.co/NVFP4/Qwen3-Coder-30B-A3B-Instruct-FP4
Base Model(s)	Qwen3 Coder 30B A3B Instruct Qwen/Qwen3-Coder-30B-A3B-Instruct
Model Size	30b
Required VRAM	18.1 GB
Updated	2026-11-02
Maintainer	NVFP4
Model Type	qwen3_moe
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-4 5.0 GB: 2-of-4 5.0 GB: 3-of-4 3.1 GB: 4-of-4
Generates Code	Yes
Model Architecture	Qwen3MoeForCausalLM
License	apache-2.0
Context Length	262144
Model Max Length	262144
Transformers Version	4.53.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Torch Data Type	bfloat16
Errors	replace

Rank the Qwen3 Coder 30B A3B Instruct FP4 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Best Alternatives to Qwen3 Coder 30B A3B Instruct FP4

Best Alternatives	Context / RAM	Downloads	Likes
...LL MASTER CODER M 1million Ctx	1024K / 84.8 GB	122	11
Qwen3 30B A3B YOYO V3	986K / 61.1 GB	11	7
...07 YOYO2 TOTAL RECALL Instruct	986K / 84.8 GB	27	1
...07 YOYO2 TOTAL RECALL Instruct	986K / 106 GB	20	0
Qwen3 30B A3B YOYO V2	986K / 61.1 GB	19	4
Qwen3 Coder 30B A3B Instruct	256K / 61.1 GB	1746771	1168
...en3 Coder 30B A3B Instruct FP8	256K / 31.2 GB	1556690	191
Rawda Coder 30B A3b	256K / 61.1 GB	662	0
Qwen3 Coder 30B A3B Instruct	256K / 61.1 GB	342	1
Securecoder 30B Pro V3 Merged	256K / 61.2 GB	116	0

Note: green Score (e.g. "73.2") means that the model is better than NVFP4/Qwen3-Coder-30B-A3B-Instruct-FP4.