Tag

Ling-3.0-tiny

Lightweight sparse-MoE LLM (7.9B params, ~1.3B activated per token) designed for hybrid multi-step reasoning and agentic tasks. Uses a KDA–MLA hybrid attention stack and a 128-expert sparse FFN; offered in BF16/FP8/INT4 for local and edge deployment.

LFM2.5-VL-3B

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.

NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4

Open-weight 30B-parameter Mixture-of-Experts LLM with 3B active params, NVFP4-quantized checkpoint, and speculative-decoding support for long-context (up to 1M tokens) agentic, chat, reasoning and tool-calling workloads optimized for NVIDIA GPUs.

S1-mini

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.

Anima-2.9B (Gazingstars123)

A 2.9B-parameter text-to-image model fine-tuned from CircleStone Labs' Anima for anime and illustration; trained on an additional 1.7M samples with a July 2026 knowledge cutoff. Designed for non-commercial creative image generation and ComfyUI integration; weights released under the CircleStone Labs Non-Commercial (derivative) license.

Qwen3.8-27B-FP8

Provides an FP8-post-trained 27B multimodal causal language model with a native vision encoder, large-context support (262,144 native, extensible to 1,000,000), controllable thinking-mode reasoning, and compatibility with common inference engines for deployment.

unsloth/Qwen3.8-27B-GGUF

Provides a 27B Qwen3.8 GGUF build for local/offline deployment, optimized with Unsloth Dynamic V3.0 quantization. Offers switchable thinking-mode, native vision-language understanding, and native long-context support (262k+ tokens).

DeepSeek-V4-Pro-0813

Provides a Mixture-of-Experts language model tuned for million-token contexts and agentic workflows, with DSpark speculative decoding, FP4/FP8 mixed-precision support, and vLLM/SGLang deployment recipes for low-latency production inference.

unsloth/Qwen3.8-27B-NVFP4

A 27B Qwen3.8 vision‑language causal transformer quantized to NVFP4 for lower‑memory inference. Provides 262K native context (extensible to 1M), Unsloth Dynamic V3.0 4‑bit quantization and MTP support so Qwen3.8‑class multimodal workloads can run on 24GB‑class GPUs.

TeleOCR

Performs unified parsing of digital and camera-captured documents (layout, text, tables, formulas) using a ~1.2B-parameter vision–language model. Key differences: geometry-aware modeling, curvature-guided sampling, and content-structure decoupled training to handle real-world deformations without separate dewarping.

Ultra-FineWeb-L1

Provides an L1 filtered English web corpus from recent Common Crawl snapshots for LLM pretraining, including main-text extraction, language and heuristic filtering, sensitive-field replacement, customized cleaning, and MinHash deduplication; contains 1T+ tokens across ~1.14B documents with structured metadata fields.

Qwen3.8-27B RVN Heretic Abliterated Uncensored (GGUF)

Provides uncensored variants of Qwen3.8-27B modified with ARA (Arbitrary-Rank Ablation) to surgically remove refusal behavior, packaged as GGUF quant files for local llama.cpp inference. RVN applies two extra ARA passes that reduce harmful-prompt refusals to 0–1/100 with very low KL damage; intended for adult research/creative use and reduces safety guardrails.