AI Model2026
Provides a GGUF-quantized build of GLM-5.3-Flash for local text-generation and inference. Key features: 320B total / 18B active parameters, hybrid sparse+linear attention, native multimodal pretraining and Unsloth Dynamic quantization. Best for developers running GGUF local inference workflows.
AI Model2026
Integrates a pretrained vision–language model with a BEV perception head and a Planning Expert to provide 3D perception, driving VQA and motion planning for autonomous driving while keeping the base VLM architecture unchanged.
AI Model2026
A 770B-parameter Mixture-of-Experts instruct model from Tencent that natively supports 1,048,576-token contexts, Gated DSA attention, and speculative MTP decoding; open-sourced under Apache-2.0 with BF16 and FP8 weights for deployable inference.
AI Model2026
Drop-in abliterated (refusal-removed) build of GLM-5.3-Flash that bakes refusal-direction removal into block-FP8 safetensors, yielding an uncensored 320B (18B active) multimodal MoE model with a 1M-token context. Intended for red-teaming, interpretability, and robustness research; MIT license; not for production without added guardrails.
AI Model2026
An experimental multimodal model that adds visual understanding to DeepSeek-V4-Flash: accepts text+image inputs and returns text analyses. Improves vision-dependent agent workflows while maintaining comparable text-only performance; released under an MIT license on Hugging Face.
AI Model2026
Sparse MoE causal LLM that uses Mixture-of-Value Attention (MoVA) to store 36B parameters while activating ~4B per token; supports a native 524,288-token context and is released with final checkpoints, training data, and training code under open license.
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.
Introduces Declarative Attention (DA), a zero-shot protocol that has LMs declare which parts of long context to attend to during chain-of-thought, letting the runtime build dynamic attention masks and skip most KV-cache reads. Produces large token savings (up to ~52% on Gemma-4-31B) with modest accuracy loss.
AI Model2026
Fine-tuned variant of Qwen3.8-27B optimized to reduce reasoning cost and wall-clock latency for long-running agent workloads. Delivers ~12.8% faster decoding and higher MTP draft acceptance while cutting runaway reasoning, at a small MMLU-Pro accuracy trade-off (−1.45 pp).
Evaluates layer dropout (stochastic depth) in LLM pretraining, finds optimal layer distributions and time schedules that save ~20–25% training FLOPs at comparable or lower validation loss, and enables zero-shot layer skipping and self-speculative decoding for up to ~1.4–1.5× inference speedup.
AI Model2026
Multimodal foundation model for visual understanding, spatial reasoning and multi-step agent tool use — accepts text, multiple images and video at any resolution and supports long contexts (up to 128K tokens). Emphasizes fine-grained 2D/3D relations, affordance reasoning and embodied-AI planning.
AI Model2026
Post‑trained 9B causal language model optimized for agentic workflows, tool use, coding, and long‑context instruction following. Uses a routing‑guided agentic post‑training pipeline that converts harness executions into training signal, improving agentic and coding benchmarks. Text‑only weights (safetensors/BF16), Apache‑2.0.