Parameters: 2.8T total (104B activated)Quantization: MXFP4 weights / MXFP8 activations (native quantization-aware release from Moonshot AI)Context: 256K tokensStrengths: Native image understanding, visual reasoning, document analysis, screenshot-to-code generation, and vision-guided agentic workflowsBest for: Visual knowledge work, document understanding, design-to-code workflows, and multimodal agentsModel weights: moonshotai/Kimi-K3Configuration repo: tinfoilsh/confidential-kimi-k3
Multimodal: Supports text and image inputs with native reasoning and tool calling. See Image Processing Guide for usage examples.

GLM-5.3 Flash
glm-5-3-flashMultimodal: Supports text and image inputs with always-on reasoning and tool calling. See Image Processing Guide for usage examples.

DeepSeek V4.1 Flash
deepseek-v4-1-flashMultimodal: Supports text and image inputs with optional reasoning and tool calling. See Image Processing Guide for usage examples.

Gemma 4 31B
gemma4-31bMultimodal: Supports variable aspect ratios and configurable image token budgets for balancing speed and detail. See Image Processing Guide for usage examples.



