What are the hardware requirements for MiroThinker 1.7 Mini?

MiroThinker 1.7 Mini 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 1.7 Mini and how large is it?

MiroThinker 1.7 Mini is developed by miromind-ai, a model with 235b 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 1.7 Mini?

MiroThinker 1.7 Mini is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

MiroThinker 1.7 Mini by miromind-ai — VRAM 61.1GB, 256K context

Name: MiroThinker 1.7 Mini
Author: miromind-ai

MiroThinker 1.7 Mini is an open-source language model by miromind-ai. Features: 235b LLM, VRAM: 61.1GB, Context: 256K, License: apache-2.0, LLM Explorer Score: 0.26.

Arxiv:2511.11793 Arxiv:2603.15726 Agent Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-235b-a22... Conversational Deep-research Deploy:azure En Endpoints compatible Miromind Open-source Qwen3 moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/miromind-ai/MiroThinker-1.7-mini

MiroThinker 1.7 Mini Parameters and Internals

LLM Name	MiroThinker 1.7 Mini
Repository 🤗	https://huggingface.co/miromind-ai/MiroThinker-1.7-mini
Base Model(s)	Qwen3 235B A22B Thinking 2507 Qwen/Qwen3-235B-A22B-Thinking-2507
Model Size	235b
Required VRAM	61.1 GB
Updated	2026-08-05
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	apache-2.0
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 1.7 Mini 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

Quantized Models of the MiroThinker 1.7 Mini

Model	Likes	Downloads	VRAM
MiroThinker 1.7 Mini Mlx 4Bit	2	37	17 GB

Best Alternatives to MiroThinker 1.7 Mini

Best Alternatives	Context / RAM	Downloads	Likes
...en3 235B A22B Instruct 2507 1M	986K / 171.9 GB	4	1
Qwen3 235B A22B Instruct 2507	256K / 167.9 GB	28	10
Qwen3 235B A22B Thinking 2507	256K / 167.9 GB	14	3
Qwen3 235B A22B Instruct 2507	256K / 171.9 GB	59472	793
Vivo C V1	256K / 156.4 GB	415	2
... 235B A22B Thinking 2507 NVFP4	256K / 139.2 GB	22828	8
... 235B A22B Instruct 2507 NVFP4	256K / 139.2 GB	14322	10
Qwen3 235B A22B Thinking 2507	256K / 171.9 GB	20387	408
...n3 235B A22B Instruct 2507 FP8	256K / 236.5 GB	54126	147
...n3 235B A22B Thinking 2507 FP8	256K / 236.5 GB	46813	86

Note: green Score (e.g. "73.2") means that the model is better than miromind-ai/MiroThinker-1.7-mini.