Silk Compute

GLM 5.3 Uncensored is an uncensored variant of Z.ai's GLM-5.3, with refusal behavior removed through abliteration and further fine-tuning. It takes text input and output with a 1M-token context window, always reasons at low, high or max depth, and is aimed at red teaming, security research and agent testing.

DeepSeek V4.1 Flash 1017 Uncensored is an abliterated, uncensored variant of DeepSeek V4.1 Flash 1017, a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance and no content-filtering guardrails.

GLM 5.3 Flash Uncensored is Z.ai's GLM-5.3-Flash with refusal behavior removed. The base model is a Mixture-of-Experts model with 320B total and 18B active parameters that combines sparse and linear attention to lower long-context cost, reasons at low, high or max effort, and is aimed at coding and agentic tasks. This variant has a 1M-token context window.

Kimi K3.1 Pro Uncensored is Moonshot AI's Kimi K3.1 Pro with refusal behavior removed. The base model is post-trained from Kimi K3, a Mixture-of-Experts model with 2.8T total and 104B active parameters and a 1M-token context window, and reasons at low, high or max effort for coding, research and agentic tasks. This variant takes text input and produces text output.

Hy4 Uncensored is the Tencent Hy Team's Hy4 with refusal behavior removed. The base model is a 770B-parameter Mixture-of-Experts model with 49B parameters active per token and a 1M-token context window, using Gated DeepSeek Sparse Attention, and is post-trained for software engineering, office and data analysis work and scientific research, with adjustable reasoning effort. This variant takes text input and produces text output.