ledgernova/sn120-660618710710

TEXT GENERATIONPricing:Input $0.4 / Cached $0.07 / Output $4Concurrent Unit Cost:3Model Size:35.1BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 16, 2026Architecture:Transformer Featherless Exclusive Cold

The ledgernova/sn120-660618710710 model is a 35.1 billion parameter language model, LoRA-merged from kevin954/Affine-5dfqbbh8ev-sft. With a context length of 32768 tokens, this model is currently a private TTL insurance checkpoint. It is not yet a public submission and is undergoing internal evaluation.

Loading preview...

Model Overview

The ledgernova/sn120-660618710710 is a substantial 35.1 billion parameter language model, developed by ledgernova. It has been created through a LoRA merge process, originating from the kevin954/Affine-5dfqbbh8ev-sft checkpoint. This model features a significant context window of 32768 tokens, allowing it to process and generate extensive text sequences.

Key Characteristics

  • Parameter Count: 35.1 billion parameters, indicating a large and potentially capable model.
  • Context Length: Supports a 32768-token context window, suitable for tasks requiring long-range understanding and generation.
  • Origin: LoRA-merged from kevin954/Affine-5dfqbbh8ev-sft.

Current Status

This model is currently designated as a private TTL (Time-To-Live) insurance checkpoint. It is not yet intended for public use or as a final submission, as it is undergoing internal evaluation and has not cleared its Stage-5 gate. Developers should note its developmental status and that it is not yet ready for general application.