MiroThinker 1.7 Int4 AutoRound by Intel

 ยป  All LLMs  ยป  Intel  ยป  MiroThinker 1.7 Int4 AutoRound   URL Share it on

MiroThinker 1.7 Int4 AutoRound is an open-source language model by Intel. Features: 32.6b LLM, VRAM: 47.3GB, Context: 256K.

  Arxiv:2309.05516   4-bit   Auto-round Base model:miromind-ai/mirothi... Base model:quantized:miromind-...   Conversational   Qwen3 moe   Region:us   Safetensors   Sharded   Tensorflow
MiroThinker 1.7 Int4 AutoRound (Intel/MiroThinker-1.7-int4-AutoRound)
๐ŸŒŸ Advertise your project ๐Ÿš€

MiroThinker 1.7 Int4 AutoRound Parameters and Internals

LLM NameMiroThinker 1.7 Int4 AutoRound
Repository ๐Ÿค—https://huggingface.co/Intel/MiroThinker-1.7-int4-AutoRound 
Base Model(s)  miromind-ai/MiroThinker-1.7   miromind-ai/MiroThinker-1.7
Model Size32.6b
Required VRAM47.3 GB
Updated2026-03-31
MaintainerIntel
Model Typeqwen3_moe
Model Files  1.1 GB: 1-of-117   1.1 GB: 2-of-117   1.1 GB: 3-of-117   1.1 GB: 4-of-117   1.1 GB: 5-of-117   1.1 GB: 6-of-117   1.1 GB: 7-of-117   1.1 GB: 8-of-117   1.1 GB: 9-of-117   1.1 GB: 10-of-117   1.1 GB: 11-of-117   1.1 GB: 12-of-117   1.1 GB: 13-of-117   1.1 GB: 14-of-117   1.1 GB: 15-of-117   1.1 GB: 16-of-117   1.1 GB: 17-of-117   1.1 GB: 18-of-117   1.1 GB: 19-of-117   1.1 GB: 20-of-117   1.1 GB: 21-of-117   1.1 GB: 22-of-117   1.1 GB: 23-of-117   1.1 GB: 24-of-117   1.1 GB: 25-of-117   1.1 GB: 26-of-117   1.1 GB: 27-of-117   1.1 GB: 28-of-117   1.1 GB: 29-of-117   1.1 GB: 30-of-117   1.1 GB: 31-of-117   1.1 GB: 32-of-117   1.1 GB: 33-of-117   1.1 GB: 34-of-117   1.1 GB: 35-of-117   1.1 GB: 36-of-117   1.1 GB: 37-of-117   1.1 GB: 38-of-117   1.1 GB: 39-of-117   1.1 GB: 40-of-117   1.1 GB: 41-of-117   1.1 GB: 42-of-117   1.1 GB: 43-of-117
Model ArchitectureQwen3MoeForCausalLM
Context Length262144
Model Max Length262144
Transformers Version4.57.6
Vocabulary Size151936

Rank the MiroThinker 1.7 Int4 AutoRound Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 52334 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum โ€” our secure, self-hosted AI agent for server management.
Release v20260328a