LocalClaw/LLM/MiroThinker v1.5 (30B MoE)
Public model card reference

MiroThinker v1.5 (30B MoE)

Catalogue summary: ⚠️ 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.

Repository editorial metadata; verify comparative claims in the linked upstream material.

Public model cardNo public GGUF verified30B (3B active, MoE)2026-02
Choose an app

Only verified options can be opened. Unsupported apps are clearly marked.

Compare models
LM StudioNot available for this model
UnslothNot available for this model
OllamaNot available for this model
Open on Hugging FaceModel card, licence and access details
llama.cppNot available for this model
Use with LocalClawOptional workspace after the model is installed
Source status
Public model card
Public GGUF
Not verified
Parameters
30B (3B active, MoE)
Access
Public card

Verified source status

LocalClaw verified a public model card for MiroThinker v1.5 (30B MoE) on 2026-09-07, but no public GGUF file in that repository. The catalogue RAM and quantization fields are estimates, not a verified install path.

Only the public model card was verified; no public GGUF file was verified in that repository. Open the model card to confirm current artefacts and supported runtimes. LocalClaw does not claim a one-click LM Studio install.

Public model card (no GGUF file verified 2026-09-07): miromind-ai/MiroThinker-v1.5-30B
reasoningcodepowerquality

Source availability

01
Open the model cardUse the verified upstream card as the source of truth for this record.
02
Inspect current filesNo public GGUF file was verified in the repository during the catalogue audit.
03
Confirm a supported runtimeChoose a local runtime only after verifying the exact artefact, licence and hardware requirements upstream.

Catalogue record

  • Family: mirothinker
  • Parameters: 30B (3B active, MoE)
  • Recommended quantization: Q4_K_M
  • Catalogue minimum RAM: 48 GB
  • Catalogue model size: 18 GB
  • Tags: reasoning, code, power, quality

Practical limits

  • Catalogue RAM is a minimum estimate, not a guarantee for every context length or runtime.
  • Speed and memory use vary by quantization, backend, context length and system headroom.
  • Verify architecture, licence and usage restrictions in the linked upstream material before deployment.

Catalogue tags

  • reasoning
  • code
  • power
  • quality

Capability profile

Repository catalogue ratings used by LocalClaw's editorial rubric. They are not a standardized third-party benchmark.

speed
3
quality
9
coding
8
reasoning
10

Technical notes

Developer
See upstream repository
License
See upstream repository
Context window
See upstream repository
Architecture
See upstream repository

Related catalogue entries

Linked mechanically by family, shared tags and nearby RAM tier; this is not a quality ranking.

MiroThinker 1.7 (30B MoE) 30B (3B active, MoE)MiroThinker 1.7 Mini (30B MoE) 30B (3B active, MoE)Llama-3.3-Nemotron-Super (49B) 49BQwen 3 (32B) 32BQwen 3 Next (80B/3B MoE) 80B (3B active)Qwen 3.6 (27B) 27BMuse Glimmer 30B 29.8B multimodalQwen 3.5 MoE (122B/10B active) 122B (10B active)

Where to go next