Tag

LFM2.5-230M

230M-parameter multilingual instruction-tuned text-only LLM for on-device agentic pipelines and data extraction; 32K context, 19T-token pretraining, optimized for fast CPU/edge inference (e.g., 213 tok/s on Galaxy S25 Ultra, 42 tok/s on Raspberry Pi 5); not for heavy reasoning or complex code generation.

Inflect-Nano-v2

Generates English speech locally from text into 24 kHz waveforms with a fixed synthetic male voice. Complete text-to-waveform TTS under ~4M parameters (≈16 MB FP32), supports CPU/CUDA inference, deterministic seeds, long-text chunking and an ONNX export path under Apache-2.0 license.

Ornith-1.0-35B-GGUF

A self-improving, agentic coding LLM tailored for terminal-style coding agents and tool-calling, provided as 35B MoE GGUF weights with very large context support. Trained with reinforcement learning to jointly generate task scaffolds and solutions; designed for local inference and OpenAI-compatible tool endpoints.

Huihui-GLM-5.2-abliterated-GGUF

An uncensored GGUF build of GLM-5.2 that applies weight “abliteration” to remove refusal filters and produce a locally runnable text-generation model; includes quantization conversions and shard-merge instructions, intended for experimental research rather than production use.

Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots

Provides a portable C++ inference runtime to deploy embodied AI models (vision–language–action and world–action) on heterogeneous robot hardware, enabling latency-first batch-1 closed-loop control. Key features include modular multi-rate layers, fused low-latency inference, and extensible head/IO plugins.

Hy3

Provides a large Mixture-of-Experts instruct LLM (295B total parameters, 21B active, 256K context) optimized for reasoning, long-context retention and agent workflows; open-sourced under Apache-2.0.

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.

Bonsai-27B-gguf

Runs a full 27B-class Qwen3.6-derived language model in a ~3.9 GB 1-bit GGUF pack for on-device inference with a 262K-token context; true 1.125 bits/weight binary representation, DSpark speculative drafter, and llama.cpp (CUDA/Metal/CPU) support.

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.

Supra-Router-51M

Decides whether a user prompt should be executed locally on an edge small LLM or routed to a larger cloud model, emitting a deterministic pipe-separated decision string. A 51.7M micro-LLM fine-tuned with multi-task sequence generation to predict domain, complexity and code/math flags, optimized for ultra-low latency edge routing.

Prompt Routing Dataset

Provides labeled prompts with full-reference answers (including chain-of-thought and code blocks) and per-example metadata to train edge routing/orchestrator models that decide whether to handle inputs locally or route them to larger models. Includes complexity scores, coding/math flags, routing justifications, and an automated override rule; suited for fine-tuning small models (50M–1.5B) for edge deployment.

ThinkingCap: Qwen 3.6 27B

Fine-tuned variant of Qwen3.6-27B that cuts internal reasoning (‘thinking’) token usage by roughly 46% on average while preserving benchmark accuracy and safety behavior. Targets lower latency and inference cost; ships on Hugging Face with GGUF quantizations for local use.