LocalClaw/LLM/MiroThinker v1.5 (30B MoE)
Open-weight MoE

MiroThinker v1.5 (30B MoE)

⚠️ Despite the small active count, this is a full 30B MoE model (Qwen3-30B-A3B base). ~82 GB full weights (Q4_K_M ≈18 GB). Deep-research agent with 256K context, tool calls, multilingual (EN/ZH). Requires H100 80 GB or serious multi-GPU. Not suitable for M1/M2 or consumer GPUs. Apache 2.0.

64 GB workstation 48 GB RAM Q4_K_M Coding assistant
Run with LocalClaw Compare all models
Parameters
30B (3B active, MoE)
Minimum RAM
48 GB
Model size
18 GB
Quantization
Q4_K_M

Can MiroThinker v1.5 (30B MoE) run locally?

MiroThinker v1.5 (30B MoE) is best for 64 GB workstations and larger Apple Silicon or NVIDIA setups.

Search for mirothinker-v1.5-30b in LM Studio or another GGUF-compatible runtime.

miromind-ai/MiroThinker-v1.5-30B
reasoningcodepowerquality

Install path

01
Check RAM fitMinimum 48 GB RAM. Start with the Q4_K_M quant.
02
Load the modelSearch mirothinker-v1.5-30b in LM Studio.
03
Control locallyUse LocalClaw to manage models, agents, chat, channels and scheduled OpenClaw work.

Strengths

  • ⚠️ Despite the small active count, this is a full 30B MoE model (Qwen3-30B-A3B base). ~82 GB full weights (Q4_K_M ≈18 GB). Deep-research agent with 256K context, tool calls, multilingual (EN/ZH). Requires H100 80 GB or serious multi-GPU. Not suitable for M1/M2 or consumer GPUs. Apache 2.0.

Limitations

  • Performance depends on quantization, RAM bandwidth and runtime support.

Best use cases

  • reasoning
  • code
  • power
  • quality

Capability profile

speed
3
quality
9
coding
8
reasoning
10

Technical notes

Developer
mirothinker
License
See model repository
Context window
Unknown tokens
Architecture
See model card

This model fits these next steps

Hardware fit is based on LocalClaw's RAM tier, model size and quantization metadata. Always leave memory headroom for your OS and runtime.

Workstation fitMac Studio M4 Max 64GBCUDA workstation classNVIDIA GB10 / DGX SparkLarge local models64GB RAM guide

Where to go next