Presents a 2.8T-parameter Mixture-of-Experts multimodal model with a 1-million-token context window and 104 billion activated parameters, targeting long-horizon agentic RL, coding, reasoning, and vision. Key innovations include Kimi Delta Attention, Attention Residuals, Stable LatentMoE (16 of 896 experts active per token), ~2.5× scaling efficiency over Kimi K2, and a public weight release.
AI Model2026
GGUF-quantized build of Moonshot AI's Kimi K3 for local inference: MXFP4-aware quantization, image-text-to-text pipeline support, native vision and a 1,048,576-token context window. Intended for local GGUF runtimes (vLLM, SGLang, TokenSpeed) with Kimi K3 license constraints.
AI Model2026
A 350M-parameter multilingual bidirectional masked-language encoder with an 8,192-token context window, intended for fine-tuning on classification, token-level tasks, retrieval/reranking and semantic-similarity; optimized for long-context CPU inference and on-device use.
AI Model2026
A 2.6B causal LLM post-trained for agentic workloads and long-context on-device text generation. Key features: 128K context window and vocabulary, function-calling/tool use support, agentic RL/post-training pipeline, and optimized CPU/Apple inference and multiple deployment formats; suited for agents, RAG and long-context extraction.
AI Audio2026
An end-to-end 11B full-duplex speech model for real-time conversational AI that jointly performs streaming speech understanding and generation, enabling ~450 ms turn-taking, barge‑in and live tool calling in a single unified architecture; research use only.
AI Model2026
Provides a 750-billion-parameter multilingual Mixture-of-Experts (MoE) foundation language model optimized for long-context understanding, agentic workflows, and instruction following. Key features include a 262,144-token context window, speculative decoding (MTP/DSpark), 37B active parameters, 10-language support, and an Apache-2.0 license.
AI Model2026
An OpenAI-compatible LLM checkpoint optimized for agentic and long-context scenarios, shipping DSpark speculative decoding and vLLM/SGLang deployment recipes; tailored for code-agent and multi-step reasoning workloads and released under MIT.
AI Model2026
Enables local use of a GGUF-quantized DeepSeek-V4-Flash-0731 via Unsloth Dynamic quantizations; provides a Q8 (162GB) lossless option and smaller Q4 variants for lower-memory inference and agentic scenarios using Unsloth tooling.
AI Model2026
Provides a GGUF-quantized, llama.cpp-compatible build of LiquidAI's LFM2.5-2.6B for local CPU inference and offline deployment. Supports multilingual generation and long-context workflows; optimized for low-memory, on-device use.
AI Model2026
Finetunes Qwen3.6‑35B using an adversarial generator–critic loop that synthesizes ~10,000 verifiable “frontier” tasks to boost scientific research, long‑horizon reasoning, coding and tool use; supports an extended 262,144‑token context and common serving stacks.
AI Model2026
A 35B additive ternary-quantized variant of Mach-1 that aims to preserve most capabilities of its BF16 teacher while reducing compute and memory; shows ~95% mean retention across 12 benchmarks and competitive per-task parity on several evaluations.
AI Model2026
Provides GGUF-quantized, ComfyUI-ready MiniMax‑H3 model files (FL2VA/REF2VA, text encoder, audio/video VAEs) to enable local ComfyUI inference for short video + stereo audio generation; requires the official VAEs and sufficient VRAM.