LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

MiroThinker 1.7 by miromind-ai

 »  All LLMs  »  miromind-ai  »  MiroThinker 1.7   URL Share it on

  3489   

MiroThinker 1.7 is an open-source language model by miromind-ai. Features: 235b LLM, VRAM: 220GB, Context: 256K, License: apache-2.0, LLM Explorer Score: 0.39.

  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 

MiroThinker 1.7 Benchmarks

LLME Score: 0.39231
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
MiroThinker 1.7 (miromind-ai/MiroThinker-1.7)
🌟 Advertise your project 🚀

MiroThinker 1.7 Parameters and Internals

LLM NameMiroThinker 1.7
Repository 🤗https://huggingface.co/miromind-ai/MiroThinker-1.7 
Base Model(s)  Qwen3 235B A22B Thinking 2507   Qwen/Qwen3-235B-A22B-Thinking-2507
Model Size235b
Required VRAM220 GB
Updated2026-04-18
Maintainermiromind-ai
Model Typeqwen3_moe
Model Files  5.0 GB: 1-of-95   5.0 GB: 2-of-95   5.0 GB: 3-of-95   5.0 GB: 4-of-95   5.0 GB: 5-of-95   5.0 GB: 6-of-95   5.0 GB: 7-of-95   5.0 GB: 8-of-95   5.0 GB: 9-of-95   5.0 GB: 10-of-95   5.0 GB: 11-of-95   5.0 GB: 12-of-95   5.0 GB: 13-of-95   5.0 GB: 14-of-95   5.0 GB: 15-of-95   5.0 GB: 16-of-95   5.0 GB: 17-of-95   5.0 GB: 18-of-95   5.0 GB: 19-of-95   5.0 GB: 20-of-95   5.0 GB: 21-of-95   5.0 GB: 22-of-95   5.0 GB: 23-of-95   5.0 GB: 24-of-95   5.0 GB: 25-of-95   5.0 GB: 26-of-95   5.0 GB: 27-of-95   5.0 GB: 28-of-95   5.0 GB: 29-of-95   5.0 GB: 30-of-95   5.0 GB: 31-of-95   5.0 GB: 32-of-95   5.0 GB: 33-of-95   5.0 GB: 34-of-95   5.0 GB: 35-of-95   5.0 GB: 36-of-95   5.0 GB: 37-of-95   5.0 GB: 38-of-95   5.0 GB: 39-of-95   5.0 GB: 40-of-95   5.0 GB: 41-of-95   5.0 GB: 42-of-95   5.0 GB: 43-of-95   5.0 GB: 44-of-95
Supported Languagesen
Model ArchitectureQwen3MoeForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version4.51.1
Vocabulary Size151936
Torch Data Typebfloat16

Best Alternatives to MiroThinker 1.7

Best Alternatives
Context / RAM
Downloads
Likes
...en3 235B A22B Instruct 2507 1M986K / 171.9 GB121
Qwen3 235B A22B Instruct 2507256K / 171.9 GB183785772
MiroThinker 1.7 Mini256K / 61.1 GB179486
Qwen3 235B A22B Instruct 2507256K / 167.9 GB1889
Qwen3 235B A22B Thinking 2507256K / 167.9 GB772
Qwen3 235B A22B Thinking 2507256K / 171.9 GB79700404
...n3 235B A22B Instruct 2507 FP8256K / 236.5 GB239764147
... Nemotron 235B A22B GenRM 2603256K / 195 GB160724
...n3 235B A22B Thinking 2507 FP8256K / 236.5 GB3695882
... 235B A22B Instruct 2507 NVFP4256K / 139.2 GB38826

Rank the MiroThinker 1.7 Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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  

What open-source LLMs or SLMs are you in search of? 52996 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer