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.
Multimodal vision-language model optimized for on-device image+text tasks: image captioning, full-page OCR with layout annotation, grounding/bounding-box prediction, and function calling. Built on the LFM2.5-2.6B backbone with a SigLIP2 NaFlex 400M vision encoder and tuned for low-latency, low-memory edge inference.
Converts raw ASR transcripts into clean written text: adds punctuation and capitalization, expands spoken numbers/dates/times/currencies/emails, removes fillers and resolves self-corrections. Fine-tuned from Qwen3-0.6B (≈0.6B params), 94.8% token accuracy on a 7,519-case English test set; designed for CPU/edge deployment and deterministic post-processing.
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.
Turns a context, a question, and 2–20 candidate answers into a single chosen option for classification, routing, ordered scores, and Boolean decisions. Built on mmBERT-small with a 144.3M-parameter decision head, runs on CPU with up to 8,192 combined tokens; FP32 weights occupy 550.5 MiB and are Apache‑2.0 licensed.
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.
Transcribes English speech into punctuated, capitalized text — a 164 MB quantized ASR model that averages 5.21% WER across seven Open ASR Leaderboard sets. Optimized for on-device and CPU/GPU inference, with fast runtimes on Apple M5 and Docker/GPU support.
On-device speech-to-text for short clips (up to 30s) in seven languages, yielding transcripts, word-level timestamps and per-frame speech embeddings in a single 16.9 MB model. Runs on the Needle CPU engine with 2–4 bit quantization, supports keyword biasing and returns empty transcripts for silence.
GGUF (llama.cpp) quantized build of MiniCPM‑V 4.7 35B‑A3B for local/CPU and on-device multimodal image/video→text inference; supports imatrix mixed quantization, Lookahead Expert Scheduling and DSpark speculative decoding to reduce expert-loading stalls and improve throughput.
Turns PDFs and images into readable markdown, plain text, or JSON with per-line and per-block boxes and reading order. Uses ~18 MB ONNX models (1M-parameter recognizer) optimized for CPU throughput (up to 49 pages/s, ~230 ms median/page) and layout extraction; not ideal for complex tables, handwriting or degraded scans.
Performs zero-shot probabilistic multivariate time-series forecasting with up to 32,768-step history and 21 quantile outputs; implemented as a 209M-parameter patch-based transformer supporting past and known-future covariates and CPU-friendly inference.
Compiles a deterministic RISC-V CPU into a language model’s weights, enabling exact arithmetic and C or MicroPython execution without an external tool runtime. It uses Gated DeltaNet state as memory and remains experimental.