L3 8B Lunaris v1 Turbo is an optimized build of Sao10K's Lunaris generalist merge, sharing the same 8 billion parameter Llama 3 base and 8K context window. Lunaris is assembled as a TIES merge that uses int8 masking and rescaling with density-weighted merging, blending several Llama 3 roleplay and instruction models. Like the base model, it targets roleplay, dialogue generation, and balanced reasoning, keeping character consistency across multi-turn exchanges. The "Turbo" build is a quantized deployment of the same recipe rather than a separately trained model. It suits chatbots, interactive fiction, and conversational endpoints where the qualities of the Lunaris merge are a good fit. Use the base Lunaris settings as a starting point: temperature 1.4 and min_p 0.1 with the Llama 3 Instruct template.
L3 8B Lunaris v1 Turbo runs on 1 route through the qynio gateway. Compare residency, zero retention, and training posture at a glance — full data-handling detail per route below.
| Provider | Region | Zero data retention | Training | Input | Output |
|---|---|---|---|---|---|
| US | Zero data retention | No | $0.04 | $0.05 |
L3 8B Lunaris v1 Turbo runs on a single route through the qynio gateway today, so its availability is that provider's availability.
Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. .
Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. See uptime for every provider qynio monitors.
Each route hosting L3 8B Lunaris v1 Turbo has its own privacy posture, residency, and no-KYC terms. Postures are maintained by qynio with a last-verification timestamp.
Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. US; unknown; deposit available.
Call L3 8B Lunaris v1 Turbo through the qynio gateway with one API key. Let your coding agent set it up, or call it directly — qynio is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.
Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up qynio for you.
import OpenAI from "openai";const client = new OpenAI({apiKey: process.env.QYN_API_KEY,baseURL: "https://api.qyn.io/v3/compat",});const completion = await client.chat.completions.create({model: "deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, crypto rails, pricing, and benchmarks.
