Compresses KV cache for long-chain reasoning by keeping prompt tokens and evicting remaining entries uniformly at random per attention head; across four models and six reasoning tasks it matches the strongest prior evictor while delivering 32–43% higher vLLM throughput. Relies on prompt protection and redundancy across heads/text to retain reasoning traces; suitable when static memory budgets and higher serving throughput are priorities.
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
Open-weights preview checkpoint for a multimodal reasoning model that generates text from text and image/video inputs, exposes adjustable reasoning effort and tool-calling, and supports an extended 262,144-token context for long-horizon tasks and agent-style workflows.
AI Model2026
A 27B-class language model packaged in GGUF with end-to-end ternary weights for on-device or single-GPU llama.cpp inference; reduces FP16 footprint to ~5.9–7.2 GB while retaining ~98% of baseline performance and supporting up to 262K tokens.
AI Deploy2026
Evaluates multi-field JSON schemas in parallel to extract boolean or categorical field values from text, producing guaranteed-valid JSON and per-field calibrated confidences. Uses KV-cache broadcasting, sub-vocabulary logit slicing and token-tree disambiguation to cut latency (5.6x–7.0x on M4 Max) versus autoregressive decoding; requires Apple Silicon and MLX.
AI Audio2026
Performs low-latency streaming speech-to-text, emitting one token per selectable 80/120/160 ms clock with configurable transcription delay and a 30s rolling KV cache for unlimited 24/7 transcription. Bilingual (zh/en) and includes semantic VAD.
AI Model2026
Scores candidate actions against a textual state using contrastive state/action embeddings for very fast zero-shot ranking and typed decision-making. Built as two small projection heads on frozen Qwen3-8B; fine-tunable as a verifier for agentic benchmarks.
AI Model2026
Performs schema-driven, low-latency classification and structured decision-making over English text. Supports multi-head scoring, constrained joint decoding with confidence/feasibility metadata, span extraction, and local CPU/GPU deployment via the gliner2 runtime.
AI Model2026
Compresses Qwen3.8-27B into a 12.3 GB sensitivity-aware mixed-precision quantized checkpoint for long-horizon agent workloads; preserves BF16 fidelity (+0.02% PPL, 93.2% token Top‑1 agreement), supports 262K context and vLLM serving, text-only and Apache‑2.0 licensed.
Compresses recurrent states in linear-attention LLMs via spatial–temporal post-training quantization, allocating bits by error lifetime and per-row impact to preserve accuracy (6-bit ≈ FP32) while cutting serving memory up to 68.7%.
AI Model2026
Provides an EXL3 3.0 bits-per-weight quantization of a weight-edited GLM-5.3 UNCENSORED FP8 model for self-hosted text generation and agent workflows. Key characteristics: 753B MoE architecture, 273 GiB on disk, converted with ExLlamaV3; tool-call parsing requires preserving string arguments.