Back to fdtn-ai
fdtn-ai /

AN
antares-1b

Open WeightsChat & ReasoningtextUpdated July 21, 2026

antares-1b

Model Overview

antares-1b is a 1.8B-parameter text generation model developed by fdtn-ai. Built on the GraniteMoeHybridForCausalLM architecture. Supports en. Released on 2026-07-21.

📊 Quick Specs

Specification Table
SpecificationValue
Parameters1.8B
ArchitectureGraniteMoeHybridForCausalLM
Tasktext generation
Modalitytext
LicenseAPACHE-2.0
Frameworktransformers
MoENo
Languagesen

✨ Key Features

  • 1.8B parameters
  • Built on GraniteMoeHybridForCausalLM architecture (transformers)
  • Primary task: text generation (text modality)
  • Language support: en
  • Open-weights under APACHE-2.0 license — self-hostable and fine-tunable

📈 Community Adoption

  • 150 likes on Hugging Face
  • 4,266 downloads on Hugging Face

🔗 Resources

📜 License & Access

APACHE-2.0 — Open-weights model available for download, fine-tuning, and self-hosted deployment.

Key Features

1.8B parameters

Feature 01✦

Built on GraniteMoeHybridForCausalLM architecture (transformers)

Feature 02✦

Primary task: text generation (text modality)

Feature 03✦

Language support: en

Feature 04✦

Open-weights under APACHE-2.0 license — self-hostable and fine-tunable

Feature 05✦

You might also want to compare

Kimi K3

Moonshot AI

Specs →

Claude Opus 5

Anthropic

Specs →

KAT-Coder-V2.5-Dev

Kwaipilot

Specs →

Verified Sources

Tags

open-weightstrendinghuggingfacetransformerstext-generation

Model Specs

open-weights

Parameters

1.8B

Context Window

unknown

License

APACHE-2.0

Deployment

self-hostable

Resources & Links

Hugging Face

Curator Notes

Auto-ingested from HuggingFace Trending on 2026-07-25. Architecture: GraniteMoeHybridForCausalLM. Params: 1.8B. License: APACHE-2.0.

Compare Specs

Compare parameters, context windows, modalities, and benchmark scores of this model side-by-side with others.

Compare Model