LocalClaw/LLM/Trinity Large Preview (398B MoE)
Open-weight MoE

Trinity Large Preview (398B MoE)

Catalogue summary: Arcee AI's server-grade sparse MoE. The official model card lists about 398B total and 13B active parameters; the official Q4_K_M GGUF is about 241.6 GB. OpenMDW 1.1 licensed.

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

320 GB catalogue minimum320 GB RAMQ4_K_MCoding assistant
Choose an app

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

Compare models
LM StudioNot available for this model
Open in UnslothLaunches Unsloth Desktop on this model's download page
OllamaNot available for this model
Open on Hugging FaceFiles, licence and available downloads
llama.cppNot available for this model
Use with LocalClawOptional workspace after the model is installed

Desktop app links require the app to be installed. If nothing opens, LocalClaw will show app-download and model-file fallbacks.

Parameters
398B total (13B active, MoE)
Minimum RAM
320 GB
Model size
241.6 GB
Quantization
Q4_K_M

Can Trinity Large Preview (398B MoE) run locally?

Trinity Large Preview (398B MoE) has a catalogue minimum of 320 GB RAM with Q4_K_M. Actual memory use and speed vary by context length, runtime, backend and system headroom.

Treat trinity-large-preview as a server-grade catalogue target. Use the verified artefact with a compatible multi-GPU or distributed runtime and follow its upstream instructions; this is not a one-click desktop LM Studio recommendation.

Model sourcePublic GGUF repository (verified 2026-09-07): arcee-ai/Trinity-Large-Preview-GGUFUpstream releaseLicence text
chatcodereasoningpowerqualitygeneralserver-grademoe

Deployment path

01
Check RAM fitServer-grade target. Plan for 320 GB class multi-GPU memory.
02
Load the modelUse trinity-large-preview only with a compatible server-grade or distributed runtime; confirm the exact artefact and upstream instructions first.
03
Control locallyUse LocalClaw to manage models, agents, chat, channels and scheduled OpenClaw work.

Catalogue record

  • Family: trinity
  • Parameters: 398B total (13B active, MoE)
  • Recommended quantization: Q4_K_M
  • Catalogue minimum RAM: 320 GB
  • Catalogue model size: 241.6 GB
  • Tags: chat, code, reasoning, power, quality, general, server-grade, moe

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

  • chat
  • code
  • reasoning
  • power
  • quality
  • general

Capability profile

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

speed
3
quality
10
coding
10
reasoning
10

Technical notes

Developer
Arcee AI
License
OpenMDW 1.1
Context window
131,072 tokens
Architecture
Sparse Mixture of Experts, about 398B total and 13B active per token

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.

Very large memoryMac Studio Ultra classCheck model size firstNVIDIA GB10 / server optionsMore practical alternativesCompare smaller models

Related catalogue entries

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

GLM 4.6 (355B MoE) 355B (32B active)DeepSeek V3.2 (37B/685B MoE) 685B total (37B active, MoE)DeepSeek V4 Flash (284B MoE) 284B (13B active)DeepSeek V4 Flash 0731 (284B MoE) 284B (13B active)GLM 4.7 355B (32B active, MoE)GLM-5.2 (744B MoE) 744B (40B active)Qwen 3 MoE (235B/22B active) 235B (22B active)Hermes 4 (405B) 405B

Where to go next