What are the hardware requirements for MiroThinker V1.5 30B?

MiroThinker V1.5 30B requires approximately 61.1 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 MiroThinker V1.5 30B and how large is it?

MiroThinker V1.5 30B is developed by miromind-ai, 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 MiroThinker V1.5 30B?

MiroThinker V1.5 30B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

MiroThinker V1.5 30B by miromind-ai — VRAM 61.1GB, 256K context

Name: MiroThinker V1.5 30B
Author: miromind-ai

MiroThinker V1.5 30B is an open-source language model by miromind-ai. Features: 30b LLM, VRAM: 61.1GB, Context: 256K, License: mit, LLM Explorer Score: 0.25.

Arxiv:2511.11793 Agent Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-30b-a3b-... Deep-research Deploy:azure En Endpoints compatible Eval-results Miromind Open-source Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/miromind-ai/MiroThinker-v1.5-30B

MiroThinker V1.5 30B Parameters and Internals

LLM Name	MiroThinker V1.5 30B
Repository 🤗	https://huggingface.co/miromind-ai/MiroThinker-v1.5-30B
Base Model(s)	Qwen3 30B A3B Thinking 2507 Qwen/Qwen3-30B-A3B-Thinking-2507
Model Size	30b
Required VRAM	61.1 GB
Updated	2026-06-29
Maintainer	miromind-ai
Model Type	qwen3_moe
Model Files	5.0 GB: 1-of-13 5.0 GB: 2-of-13 5.0 GB: 3-of-13 5.0 GB: 4-of-13 5.0 GB: 5-of-13 5.0 GB: 6-of-13 5.0 GB: 7-of-13 5.0 GB: 8-of-13 5.0 GB: 9-of-13 5.0 GB: 10-of-13 5.0 GB: 11-of-13 5.0 GB: 12-of-13 1.1 GB: 13-of-13
Supported Languages	en
Model Architecture	Qwen3MoeForCausalLM
License	mit
Context Length	262144
Model Max Length	262144
Transformers Version	4.51.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Torch Data Type	bfloat16
Errors	replace

Rank the MiroThinker V1.5 30B 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 MiroThinker V1.5 30B

Best Alternatives	Context / RAM	Downloads	Likes
...LL MASTER CODER M 1million Ctx	1024K / 84.8 GB	163	9
... 42B A3B Thinking Total Recall	986K / 84.8 GB	26	0
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 30B A3B Instruct 2507	256K / 61.1 GB	3937	13
Qwen3 Coder 30B A3B Instruct	256K / 61.1 GB	1746771	1168
Qwen3 30B A3B Instruct 2507	256K / 61.1 GB	1903736	824
...en3 Coder 30B A3B Instruct FP8	256K / 31.2 GB	1556690	191

Note: green Score (e.g. "73.2") means that the model is better than miromind-ai/MiroThinker-v1.5-30B.