Thox-ai/ThoxFlux-350M

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:0.35BQuant:BF16Context Size:32kPublished:Aug 11, 2026License:otherArchitecture:Transformer0.0K Featherless Exclusive Cold

Thox-ai/ThoxFlux-350M is a 0.35 billion parameter language model derived from LiquidAI/LFM2.5-350M, fine-tuned by Thox-ai for chat and agent/tool-use applications. This model is specifically optimized and quantized for on-device deployment within the ThoxClip ecosystem. Its primary function is to serve as an on-device assistant and facilitate tool-routing for the THOX device program.

Loading preview...

ThoxFlux-350M Overview

ThoxFlux-350M is a compact, 0.35 billion parameter language model developed by Thox-ai. It is based on the LiquidAI/LFM2.5-350M architecture and has undergone specialized fine-tuning using Thox-ai's proprietary chat and agent/tool-use corpora. A key differentiator for this model is its optimization and quantization specifically for deployment on the ThoxClip device tier.

Key Capabilities

  • On-device assistance: Designed to function directly on THOX devices.
  • Tool-routing: Facilitates the intelligent routing and utilization of tools within the THOX device program.
  • Chat functionality: Fine-tuned for conversational interactions.

Intended Use Cases

This model is primarily intended for:

  • Serving as an on-device assistant for THOX devices.
  • Managing and routing tools within the THOX device ecosystem.

Limitations and Provenance

ThoxFlux-350M is not intended for safety-critical, medical, or legal decisions without human oversight. The base model, LiquidAI/LFM2.5-350M, is distributed under the LFM Open License v1.0 (Apache-based), which permits commercial use under certain revenue thresholds, provided the LICENSE and change notices are retained.

Finetunes
1 models