Studies looping shared transformer layers in Mixture-of-Experts models under matched budgets and proposes SMELT: loop the middle half twice while matching per-token FLOPs, non-embedding parameters, and KV cache. Shows 6.8–18.0% training-FLOPs savings on the compute-optimal frontier, stronger downstream gains on code and long-context tasks.
AI Model2026
NVFP4-quantized checkpoint of Qwen3.8-Flash-Next for GPU-optimized multimodal autoregressive inference — routed MoE experts in W4A4 NVFP4 while attention/ancillary layers remain BF16; ~2.7× smaller than the BF16 source and supports very long contexts.
AI Agent Papers2026
Presents two LLM-based search agents (Iris-mini and Iris-pro) trained by alternating supervised fine-tuning and reinforcement learning against live web search. Key features: web-graph-derived multi-hop tasks with entity abstraction, SFT–RL climbing, inference-time context management, and state-of-the-art open-source benchmark results.
AI Model2026
Provides per-tensor mixed-precision GGUF quantizations of the Qwen3.8-Flash-Next MoE model using GSQ (Gumbel-Softmax Quantization) to produce tensor-level quantized variants and RCO (Riemannian Constrained Optimization) to allocate quant types under exact size budgets; includes a BF16 vision projector and three size/bit-width operating points.
AI Model2026
A multimodal, agentic LLM optimized for long‑horizon, visually grounded workflows — capable of operating browsers and terminals and autonomously executing and testing code. Open‑source weights are available and the family ships in mini, Pro and Max variants for different compute/quality tradeoffs.
AI Model2026
Runs a 35B-class sparse MoE LLM with SSD-streamed experts, 4-bit quantization, prerouter routing prediction and Recover-LoRA adapters to enable ~2.9–3 GiB active memory and interactive decoding (~15 tok/s) for on-device inference.
AI Model2026
Multimodal agentic model for long-horizon computer and browser tasks, with visual self-correction and function-calling. The Pro variant is a 397B Mixture-of-Experts (≈17B active) model with a 262,144-token context window, Docker deployment recipes, and weights currently marked “coming soon.”
AI Model2026
A multimodal Mixture-of-Experts foundation model with a million-token context window; uses a causal encoder–decoder layout and aggressive KV-cache compression (~890 bytes/token) to limit per-token activation to 8B/16B—designed for long-context, agentic, and multimodal workloads.
An 8B native unified multimodal model that understands, reasons about, and generates high-fidelity visual content without a separate visual encoder or VAE—focused on spatially coherent patch reconstruction, native 4K generation, multi-expert distillation, and improved text rendering and image editing.
AI Model2026
Provides a drop-in checkpoint of DeepSeek-V4.1-Flash with weight-level abliteration that removes safety guardrails to produce uncensored outputs; preserves vision, MoE routing, 1M-token context and native FP8 quantization. Intended for advanced self-hosted deployment; requires large NVLink GPU domains and careful serving setup.
Generates long-form, text-controlled music with explicit arrangement and planning. Uses a 50 Hz single-codebook tokenizer, a flow-matching diffusion Transformer to predict VAE latents, and an MoE autoregressor with ABC‑CoT planning to produce 48 kHz audio up to 5m30s.
AI Model2026
Preview agentic language model for research and engineering workflows that turns research questions into executable, verifiable workflows via tool use and long-context reasoning; built on a 744B-parameter MoE (GLM-5.2) with MIT-licensed BF16 and FP8 checkpoints.