Venice Uncensored 1.1

• - 🔒 Runs inside a Trusted Execution Environment with hardware attestation.
• - 🆕 End-to-end encrypted variant for private, verifiable inference.
• - 📏 24B parameters with a 32K token context window.
• - 🔧 Apache-2.0 licensed text model from the Venice platform.
• - 🌐 Supports web search alongside its E2EE privacy mode.
• - 🎯 Enclave identity and configuration independently verifiable via attestation.
• - 💬 Part of Venice's uncensored model family.

Venice

Venice is a privacy-focused AI platform that develops its own in-house models alongside hosting third-party offerings. The organization emphasizes uncensored, unrestricted text generation as a core design principle, building models specifically tuned to…

Venice Uncensored 1.1 is a 24-billion-parameter text model offered by Venice, an AI platform. In this configuration it runs inside a Trusted Execution Environment (TEE), with hardware attestation evidence available for independent verification of enclave identity and configuration. The model ships under the Apache-2.0 license with a 32K token context window.

According to the catalog context, this variant emphasizes a privacy-oriented architecture. Running within a hardware-isolated enclave, it exposes end-to-end encryption (E2EE) as a listed capability, and its attestation report can be checked by an external party to confirm the enclave's identity and setup. Alongside this privacy mode, the model also supports web search.

Within the same product family, Venice offers newer and related options. Venice Uncensored 1.2 is a later 24B release in the broader Venice Uncensored line, while Venice Role Play Uncensored is a sibling aimed at conversational roleplay use cases. These models share Venice's general focus on uncensored text generation, with this particular entry distinguished by its TEE deployment and end-to-end encryption capability.