LocalClaw/LLM/Ornith 1.0 (397B MoE)
Public model card reference

Ornith 1.0 (397B MoE)

Catalogue summary: DeepReinforce MIT-licensed open-weight MoE derived from DeepSeek-V3.1-Terminus, tuned for agentic tool use, coding and reasoning. Official local serving examples target vLLM/SGLang on 8x80GB GPU nodes, so this is server-grade only.

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

Public model cardNo public GGUF verified397B MoE2026-06
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
397B MoE
Access
Public card

Verified source status

LocalClaw verified a public model card for Ornith 1.0 (397B 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): deepreinforce-ai/Ornith-1.0-397BUpstream releasePaper or model cardLicence text
chatcodereasoningqualityagentictool-callinggeneral

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: deepreinforce
  • Parameters: 397B MoE
  • Recommended quantization: BF16 / FP8 serving
  • Catalogue minimum RAM: 640 GB
  • Catalogue model size: 800 GB
  • Tags: chat, code, reasoning, quality, agentic, tool-calling, general

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
  • quality
  • agentic
  • tool-calling

Capability profile

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

speed
1
quality
9
coding
9
reasoning
9

Technical notes

Developer
DeepReinforce
License
MIT
Context window
See upstream repository
Architecture
Open-weight Mixture-of-Experts model derived from DeepSeek-V3.1-Terminus. The official release is distributed as safetensors and is intended for Transformers, vLLM and SGLang style serving rather than one-click GGUF desktop use.

Related catalogue entries

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

Ornith 1.0 35B GGUF 35B MoEOrnith 1.0 9B GGUF 9BGLM-5.1 754B MoEDeepSeek V3.2 Exp (671B MoE) 671B (37B active)DeepSeek V3.2 (37B/685B MoE) 685B total (37B active, MoE)

Where to go next