Tag

CubeSandbox

Provides hardware-isolated, sub-60ms, ultra-low-overhead sandboxes to run untrusted LLM/agent code. Offers event-level snapshots, kernel-level egress control, credential vaulting, and drop-in E2B SDK compatibility for high-density AI agent deployment.

SuperGemma4-26B Uncensored Fast (GGUF v2)

Provides a compact GGUF export of a tuned Gemma‑4 26B variant for local inference, optimized for llama.cpp and Apple Silicon to deliver faster, less‑censored chat and coding outputs. Includes Q4_K_M quantization and a neutral embedded template for more reliable local deployments.

MiniCPM-V 4.6

Delivers an ultra-efficient, edge-friendly multimodal image-and-video-to-text model optimized for on-device deployment. Uses mixed 4x/16x visual token compression, a low-FLOPs visual encoder, and multiple quantized variants for mobile and embedded inference.

Gemma 4 E4B — OBLITERATED v3

Removes safety refusals from a Gemma 4 E4B–based model and publishes uncensored, locally runnable GGUF/safetensors variants while preserving all tensors and fixing prior corruption. Intended for red‑teaming and offline research; not recommended for production.

Qwen3.6-35B-A3B-DFlash

Drafts multiple tokens in parallel with a lightweight block-diffusion drafter to enable speculative decoding for faster LLM inference. Designed to pair with Qwen3.6-35B-A3B and reports up to ~2.9× throughput improvements on common benchmarks.

OpenAI Privacy Filter

Detects and masks personally identifiable information (PII) in text using a bidirectional token-classification model for high-throughput, on‑premises sanitization. Key traits: 1.5B parameters, 128k-token context, Apache 2.0 license, and tunable precision/recall operating points.

unsloth/Kimi-K2.6-GGUF

Provides a GGUF-packaged, native-INT4 quantized build of the multimodal Kimi K2.6 model for image-text-to-text inference — packaged for local/self-hosted inference engines (vLLM, SGLang, KTransformers) to reduce footprint while keeping multimodal capabilities.

NVIDIA Nemotron 3 Nano Omni (30B A3B) — Reasoning (BF16)

Unified multimodal LLM for enterprise workflows: ingests video, audio, image and text to perform transcription, OCR, Q&A, summarization and long-context reasoning. Provides BF16/FP8/NVFP4 weights and integrations with vLLM, TensorRT-LLM and other runtimes.

Granite Embedding 97M Multilingual R2

Produces 384‑dim multilingual (and code) embeddings with up to 32,768 token context, optimized for low‑latency production retrieval. Compact 97M model with ONNX/OpenVINO and vLLM/GGUF deployment options for edge and high‑throughput use.

Qwen3.6-27B

A 27B multimodal causal language model with a vision encoder and native long-context support (262,144 tokens). Optimized for repository-level coding agents and multimodal understanding; includes preserved "thinking" traces, multi-token prediction (MTP), and deployment recipes for vLLM / SGLang / Transformers.

Qwen3.6-27B-FP8

FP8-quantized 27B multimodal Qwen3.6 model weights in Hugging Face Transformers format — supports image/text/video inputs, native 262k token context (extensible to ~1M), and is compatible with vLLM/SGLang/KTransformers for efficient local serving and research.

Fixed Chat Templates for Qwen 3.5 & 3.6

Drop-in Jinja chat templates for Qwen 3.5/3.6 that fix rendering errors, token waste, and tool-calling failures across runtimes (LM Studio, llama.cpp, vLLM, MLX). Adds a think-on/think-off toggle, auto-closes broken thinking tags, robust tool-argument handling, and a graceful fallback for missing user queries.