Tag

QwenPaw

Provides a deployable personal AI assistant that runs locally or in the cloud, supports multi-channel chat, extensible Skills/Plugins, and local-model runtimes. Key features include three-layer memory, kernel-level sandboxing and tool/file guards, and bundled QwenPaw-Flash local models for zero-API deployments.

G0DM0D3

A single-file, privacy-aware multi-provider chat UI that races multiple LLMs, supports local model servers, red-teaming input perturbations, and configurable telemetry for model evaluation and experimentation.

Bonsai 27B (1-bit)

Runs a full 27B-class language model using end-to-end binary (1.125-bit) weights, cutting FP16 size to ~3.9 GB. Key features: 262k-token context, custom 1-bit kernels for Apple MLX and CUDA, and an optional DSpark drafter for faster decoding. Best when memory footprint matters; trades some FP16 accuracy for on-device feasibility.

Ternary Bonsai 27B (prism-ml/Ternary-Bonsai-27B-mlx-2bit)

Runs a full 27B-class Qwen3.6-derived LLM in a ~7.2 GB ternary/2‑bit format for on-device or single‑GPU text generation, retaining ~95% of FP16 performance and supporting a 262K‑token context. Designed for laptop/GPU deployment; exceeds typical phone memory limits.

MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-GGUF

GGUF-quantized builds of a 1B 'Thinking' MiniCPM5 model fine-tuned on Fable 5 (V2) for local runtimes; enhances tool/function-calling, coding and instruction-following, and supports long contexts (up to 128K tokens).