InferX Beta Serverless GPU Inference Platform, Built for Agent-Native Workloads

L3.3-70B-Loki-V2.0

Llama-based model tuned for immersive roleplay, storytelling, and strong narrative consistency
CrucibleLab text text2text long-context

CrucibleLab/L3.3-70B-Loki-V2.0 is a 70B model fine-tuned from Llama 3.3 70B Instruct and built for long-form narrative, TTRPG-style dungeon mastering, and expressive, consistent roleplay, prioritizing creative immersion over generic assistant behavior.

Log in to deploy: this public page shows the catalog model details, but deployment and customization stay behind login.
Log in to deploy

Metadata

Provider
CrucibleLab
Modality
text
API type
text2text
Source
Created
2026-03-31 16:51:59 UTC
Updated
2026-04-06 05:13:32 UTC
Catalog version
1
Visibility
Published

Specifications

Parameters
MoE
No
Max model length
10000
Image
vllm/vllm-openai:v0.9.0

Default Deploy Config

GPU count
2
vRAM
70000 MB
Summary
2xGPU 70000 MB

Recommended Use Cases

  • General assistant

Model Spec