LLM EXPLORER 58,608 MODELS INDEXED

MiroThinker V1.5 30B by mlx-community

By mlx-community · 93 downloads
HF Repo ↗ Copy URL

MiroThinker V1.5 30B is an open-source language model by mlx-community. Features: 30b LLM, VRAM: 17.2GB, Context: 256K, License: mit, LLM Explorer Score: 0.22.

  4-bit   Agent Base model:miromind-ai/mirothi... Base model:quantized:miromind-...   Conversational   Deep-research   En   Endpoints compatible   Miromind   Mlx   Mlx-my-repo   Open-source   Qwen3 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/MiroThinker-v1.5-30B 

MiroThinker V1.5 30B Parameters and Internals

LLM NameMiroThinker V1.5 30B
Repository 🤗https://huggingface.co/mlx-community/MiroThinker-v1.5-30B 
Base Model(s)  miromind-ai/MiroThinker-v1.5-30B   miromind-ai/MiroThinker-v1.5-30B
Model Size30b
Required VRAM17.2 GB
Updated2026-08-04
Maintainermlx-community
Model Typeqwen3_moe
Model Files  5.3 GB: 1-of-4   5.4 GB: 2-of-4   5.3 GB: 3-of-4   1.2 GB: 4-of-4
Supported Languagesen
Model ArchitectureQwen3MoeForCausalLM
Licensemit
Context Length262144
Model Max Length262144
Transformers Version4.51.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to MiroThinker V1.5 30B

Best Alternatives
Context / RAM
Downloads
Likes
...LL MASTER CODER M 1million Ctx1024K / 84.8 GB1609
... 42B A3B Thinking Total Recall986K / 84.8 GB260
Qwen3 30B A3B YOYO V3986K / 61.1 GB117
...07 YOYO2 TOTAL RECALL Instruct986K / 84.8 GB271
...07 YOYO2 TOTAL RECALL Instruct986K / 106 GB200
Qwen3 30B A3B YOYO V2986K / 61.1 GB194
Qwen3 30B A3B Instruct 2507256K / 61.1 GB393713
Qwen3 Coder 30B A3B Instruct256K / 61.1 GB17467711168
Qwen3 30B A3B Instruct 2507256K / 61.1 GB1903736824
...en3 Coder 30B A3B Instruct FP8256K / 31.2 GB1556690191
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/MiroThinker-v1.5-30B.