Instructions for building an almost consumer hardware based prototype of a hearing aid
-
Updated
Oct 20, 2021 - MATLAB
#
consumer-hardware
Here are 71 public repositories matching this topic...
CodeUp: A Multilingual Code Generation Llama-X Model with Parameter-Efficient Instruction-Tuning
multilingual code-generation consumer-hardware parameter-efficient-learning instruction-tuning llama2
-
Updated
Dec 25, 2024 - Python
GLM-5.2, a 744 billion parameter mixture of experts model, in a pure C inference engine: quantized to int4, experts streamed from disk, deployed and benchmarked. Generates in 16 GB of RAM.
c machine-learning deep-learning cuda moe glm quantization systems-programming inference-engine consumer-hardware mixture-of-experts edge-ai cpu-inference int4 large-language-models llm llm-inference speculative-decoding
-
Updated
Jul 15, 2026 - C
Cross-architecture LLM internal observation database (23 models, 13 architecture families). Exposed as MCP tools for any AI coding agent.
mcp open-data transformer ai-agents consumer-hardware cross-architecture llm mechanistic-interpretability model-context-protocol anchor-dimensions frankenstein-merge
-
Updated
May 24, 2026 - Python
Capable, auditable coding that runs fully offline on a 16 GB machine. A verification-first layer (hard test execution, symbolic checking, agentic repair) that takes a local 7B to parity with its 671B teacher on verifiable tasks. MIT, pre-registered, reproducible.
reproducible-research code-generation mit-license lora ai-safety self-consistency test-driven consumer-hardware on-device-ai local-llm qwen speculative-decoding llm-interface agentic-ai deepseek-r1 math-reasoning llm-verification llama-ccp
-
Updated
Jul 6, 2026 - Python
Distributed inference infrastructure for Mixture-of-Experts models. Run large MoE models on consumer GPUs.
-
Updated
Oct 3, 2026 - Rust
Stream what shouldn't run.
cuda inference developer-tools moe glm multi-gpu kimi consumer-hardware llm local-ai speculative-decoding mixtral mixtral-8x7b deepseek glm-5-2
-
Updated
Sep 20, 2026 - Python
Making new AI run on old hardware. Authoritative database for reproducible local-AI hardware benchmarks.
-
Updated
Sep 23, 2026 - HTML
Enables building routed collections of task-specific language models with LoRA adapters that run on consumer hardware, routing queries to specialized models for improved performance without expensive API access.
routing jupyter-notebook teaching collaborative language-model fine-tuning consumer-hardware task-specific
-
Updated
Aug 11, 2026 - Python
PERSPECTIVE v2 — A 1.05 trillion parameter sparse Mixture-of-Experts language model that runs on consumer hardware (4 GB VRAM + 32 GB RAM). Features O(1) perspective decay recurrence, 3D torus manifold routing, native ternary {-1,0,+1} weights, holographic distributed memory, and hard geometric safety constraints. Built in Rust.
nlp rust machine-learning research deep-learning neural-network transformer moe language-model ai-safety efficient-inference consumer-hardware mixture-of-experts on-device-ai ternary-weights llm sparse-models holographic-memory manifold-routing novel-architecture
-
Updated
Jul 13, 2026 - Rust
Out-of-core LoRA fine-tuning and expert-routing measurement for Kimi K3 (2.78T MoE) on a 7.6 GB laptop: 93 layers streamed from a USB disk, forward checked against an independent C implementation, gradients checked by finite differences
pytorch moe offloading lora out-of-core fine-tuning consumer-hardware mixture-of-experts cpu-training llm expert-routing mxfp4 kimi-k3
-
Updated
Sep 14, 2026 - Python
Real-time audio translation using Whisper + SeamlessM4T / NLLB-200
multilingual machine-learning real-time translation ai cuda pytorch speech-recognition nmt transcription whisper audio-processing asr consumer-hardware gpu-accelerated nllb seamlessm4t
-
Updated
Jul 1, 2025 - Python
Pooling frontier LLMs across an NVIDIA RTX 4070 + a 5-year-old M1 MacBook over a $40 Thunderbolt cable. Honest, measured field records — a 70B run across both machines, and a day-old frontier MoE generating content cross-machine (framework-confirmed weight residency, byte-proven over the cable). Reproduction included.
-
Updated
Jun 30, 2026 - Python
A workbench for running large Mixture-of-Experts LLMs locally on consumer hardware with a tight VRAM budget.
-
Updated
May 31, 2026 - Python
Consumer brain-computer interface for inner speech decoding. 8-channel EEG headband ($800) outperforms 128-channel clinical systems ($50K). EEGNet 35.5% accuracy (p=0.0006), cross-subject generalization (p=0.003). Real-time demo included.
machine-learning real-time deep-learning websocket signal-processing neuroscience pytorch eeg bci brain-computer-interface assistive-technology mne-python eegnet consumer-hardware fastapi inner-speech neurotechnology neural-decoding speech-decoding thought-to-text
-
Updated
May 16, 2026 - Jupyter Notebook
实时追踪 Kickstarter 上中国背景的消费硬件项目 · 每日 cron · prelaunch / live / 已结束 · Editorial design
-
Updated
Oct 7, 2026 - HTML
GRPO training that runs until you stop it on a single RTX4090 with vllm 0.26.0 (Linux Only).
reinforcement-learning optimization cuda pytorch lora consumer-hardware local-first rlhf vllm llm-training deepseek rtx4090 grpo qwen35 grpo-training gemma4
-
Updated
Sep 26, 2026 - Python
Rabbit — independent third-party profile of a public API surface, by API Evangelist. Rabbit Inc. is a consumer technology company building AI-powered devices, best known for the Rabbit R1, a $199 handheld AI companion with industrial design by Teenage Engineering. The R1 runs rabbitOS and centers on a Large Action Model (LAM) that automates tasks a
automation company artificial-intelligence voice-assistant consumer-hardware apis-json large-action-model ai-devices
-
Updated
Oct 4, 2026
Autonomous Knowledge Induction for LLMs: Prevent catastrophic forgetting with dynamic LoRA adapters and Bayesian clustering. Your Layer 2 engine for continuous learning
bioinformatics genomics moe lora incremental-learning precision-medicine clinical-decision-support peft continual-learning catastrophic-forgetting consumer-hardware edge-ai
-
Updated
Feb 9, 2026 - Python
A fast ML library for experimentation and training on consumer hardware
machine-learning configuration ml datasets language-model inference-server finetuning consumer-hardware pretraining optimizer-algorithms llm
-
Updated
Jun 16, 2026 - Python
Add this topic to your repo
To associate your repository with the consumer-hardware topic, visit your repo's landing page and select "manage topics."