Lib.rs

› Keywords #apple-silicon #safetensors #machine-learning #rlx-models #gguf

#mlx


  1. pmetal-metal

    Metal GPU compute kernels for PMetal - FlashAttention and optimized ML primitives

    v0.5.0 #mlx #apple-silicon #fine-tuning #machine-learning #llm

  2. voice

    CLI for fast text-to-speech and speech-to-text

    v0.4.2 #text-to-speech #transcribe #mlx #listen #server #moonshine #markdown #json-rpc #mdx #cargo-binstall

  3. muthr

    Zero-trust sandbox for local inference and secure AI coding agent runtimes

    v0.1.59 #sandbox #apple-silicon #mlx #local-ai #cli #virtualization

  4. mlx-native

    Pure-Rust Metal GPU compute library for MLX-compatible inference on Apple Silicon

    v0.9.3 #mlx #apple-silicon #inference #gpu

  5. safemlx-lm

    Rust MLX language model runtime

    v0.3.1 2.6K #language-model #mlx #deep-learning #machine-learning

  6. safemlx

    Unofficial rust wrapper for Apple's mlx machine learning library

    v0.1.3 2.5K #safetensors #mlx #machine-learning #deep-learning

  7. pmetal-mlx

    MLX backend implementation for PMetal LLM fine-tuning

    v0.5.0 #apple-silicon #fine-tuning #mlx #machine-learning #llm

  8. pmetal-gguf

    GGUF file format implementation for PMetal

    v0.5.0 #mlx #apple-silicon #fine-tuning #llm #machine-learning

  9. pmetal

    High-performance LLM fine-tuning framework for Apple Silicon

    v0.5.0 #apple-silicon #fine-tuning #mlx #machine-learning #llm

  10. metaltile-std

    MetalTile kernel standard library — benchmark metadata and type definitions

    v0.1.0 #mlx #benchmark #kernel #type-definition #gpu

  11. rlx-collectives

    In-graph collective ops (all-reduce) for tensor-parallel RLX execution

    v0.2.12 #tensor-parallel #collective #rlx #kernel #graph #process-group #mlx #gpu #group-id #sums

  12. quill-mlx

    Rust bindings for Apple's MLX machine learning framework, with Metal memory management

    v0.25.5 #deep-learning #mlx #machine-learning

  13. pmetal-mlx-rs

    pmetal-maintained fork of mlx-rs: unofficial rust wrapper for Apple's mlx machine learning library

    v0.25.8 #deep-learning #machine-learning #mlx

  14. mlx-models

    Model architectures and weight loading for mlx-server (LLaMA, Mistral, Qwen2/3)

    v0.1.3 #llama #model #mlx #mistral #qwen2 #moe #local-models #tok #apple-silicon

  15. mlx-roadmap

    MLX development roadmap and planning tools

    v0.1.0 #mlx #ci-cd #roadmap #planning #active #shared-infrastructure #agent-workflow #aws #authentication #shared-state

  16. encodec-rs

    Pure Rust EnCodec runtime with native ECDC encode/decode

    v0.1.0 #decode #encode #onnx #wasm-native #mlx #lm #round-trip

  17. mlxrs

    Safe Rust bindings for Apple's MLX array framework, with LM, VLM, audio, and embeddings support

    v0.1.0 #mlx #llm #machine-learning #apple-silicon

  18. tnk

    Zero-trust sandbox for local inference and secure AI coding agent runtimes

    v0.1.2 #sandbox #apple-silicon #mlx #local-ai #cli #virtualization

  19. burn-mlx

    MLX backend for Burn deep learning framework - native Apple Silicon GPU acceleration

    v0.1.2 #apple-silicon #gpu #burn #mlx #machine-learning

  20. rlx-qwen3

    Qwen3 decoder LM for RLX

    v0.2.6 #gguf #safetensors #qwen3 #rlx-models #mlx #lm #kv-cache #text-to-speech #cargo-run #rocm

  21. rlx-flux2

    FLUX.2 rectified-flow image model for RLX

    v0.2.5 #gguf #safetensors #mlx #rlx-models #text-encoder #qwen3 #flux #cuda #hir #cargo-run

  22. cohere-transcribe-rs

    CohereLabs/cohere-transcribe-03-2026 speech-to-text model. Includes a CLI and an OpenAI-compatible API server.

    v0.1.1 #text-to-speech #libtorch #transcription #mlx #asr

  23. rlx-locateanything

    NVIDIA LocateAnything-3B VLM (MoonViT + Qwen2.5-3B) for RLX

    v0.2.6 #jpeg #mlx #nvidia #lm #cpu #image-path #qwen2 #hf-hub #wgpu #vulkan

  24. voice-tts

    Rust TTS library backed by MLX, starting with Kokoro

    v0.2.1 #text-to-speech #kokoro #mlx #hugging-face #cache #phoneme #apple-silicon

  25. rlx-sam3

    SAM 3 for RLX

    v0.2.5 #gguf #safetensors #rlx-models #sam #mlx #cargo-run #graph-builder #embedding #video #apple-silicon

  26. pmetal-lora

    LoRA and QLoRA implementations for PMetal

    v0.5.0 #apple-silicon #fine-tuning #mlx #machine-learning #llm

  27. mlex

    Safe, idiomatic Rust runtime for Apple MLX: quantized LLM inference (Qwen, Gemma4, NemotronH, DharaAR, ...) with multi-modal support

    v0.1.0 #llm-inference #apple-silicon #mlx #llm #api-bindings

  28. pmetal-merge

    Model merging toolkit for PMetal - SLERP, TIES, DARE, and more

    v0.5.0 #apple-silicon #mlx #fine-tuning #machine-learning #llm

  29. rlx-sam-ir

    Shared SAM / SAM2 mask-decoder IR helpers

    v0.2.6 #rlx-models #sam #mask-decoder #cargo-run #gguf #mlp #safetensors #mlx #qwen3 #cargo-workspace

  30. pmetal-bridge

    Zero-allocation MLX bridge — standalone C++ layer that replaces mlx-rs

    v0.5.0 #mlx #apple-silicon #fine-tuning #machine-learning #llm

  31. pmetal-models

    LLM model architectures for PMetal

    v0.5.0 #apple-silicon #fine-tuning #mlx #machine-learning #llm

  32. rlx-ocr

    OCR engine for RLX — text detection + recognition

    v0.2.6 #safetensors #rlx-models #mlx #ocr #detect #text-detection #cargo-run #cuda #rocm #rten

  33. qwen3-asr-rs

    Pure Rust implementation of Qwen3 ASR (Automatic Speech Recognition) with libtorch and MLX backends

    v0.2.0 #text-to-speech #safetensors #mlx #qwen3 #libtorch #asr #audio #audio-format #audio-transcription #model-weights

  34. pmetal-trainer

    Training loops and optimization for PMetal

    v0.5.0 #fine-tuning #apple-silicon #machine-learning #mlx #llm

  35. rlx-wav2vec2-bert

    Wav2Vec2-BERT speech encoder for RLX

    v0.2.6 #rlx-models #mlx #encoder #speech #model #cargo-run #gguf #apple-silicon #safetensors #hf

  36. mlx-rs-burn

    Unofficial rust wrapper for Apple's mlx machine learning library (fork with slice, scatter, flip operations for burn-mlx)

    v0.25.5 150 #deep-learning #mlx #machine-learning #burn

  37. pmetal-distributed

    Distributed training and inference backend for PMetal (Home Clusters)

    v0.5.0 #llm-inference #p2p #apple-silicon #peer-id #back-end #mlx #mdns #peer-discovery #election #top-k

  38. rlx-embed

    RLX embedding runtime (BERT / NomicBERT / NomicVision)

    v0.2.5 #gguf #safetensors #rlx-models #mlx #cpu #bert #embedding #cargo-run #apple-silicon #hf

  39. rlx-vjepa2

    V-JEPA 2 video encoder for RLX

    v0.2.6 #video-encoder #rlx-models #mlx #devices #graph-builder #cargo-run #gguf #predictor #safetensors #embedding

  40. rlx-voxtral

    Mistral Voxtral speech LM for RLX (Whisper encoder + Llama decoder)

    v0.2.6 #speech #llama #rlx-models #mlx #language-model #lm #voxtral #whisper #audio #gguf

  41. wax-bench

    Benchmark types and helpers for wax

    v0.1.0 #benchmark #wax #gguf #safetensors #helper #llama #config-json #mlx #llm

  42. pmetal-cli

    Command-line interface for PMetal LLM fine-tuning

    v0.3.7 #apple-silicon #fine-tuning #mlx #machine-learning #llm

  43. rlx-dinov2

    DINOv2 ViT encoder for RLX

    v0.2.6 #gguf #safetensors #rlx-models #mlx #qwen3 #din-ov2 #cargo-run #sam #vit #candle

  44. pmetal-mcp

    MCP server exposing PMetal ML toolkit

    v0.5.0 #mlx #apple-silicon #fine-tuning #machine-learning #llm

  45. am-compact

    Qwen3 inference engine with Attention Management KV-cache compaction (CUDA + Apple Silicon via MLX)

    v0.3.0 #inference-engine #safetensors #apple-silicon #mlx #qwen3 #compaction #bf16 #compacted #hugging-face #gpu

  46. rlx-voxtral-tts-train

    RLX autodiff training for Voxtral voice cloning — codec encoder + LoRA

    v0.2.6 #safetensors #rlx-models #lora #text-to-speech #mlx #automatic-differentiation #voice-cloning #voxtral #gguf #cargo-run

  47. pmetal-distill

    Knowledge distillation toolkit for PMetal - KL divergence, hidden state alignment, and offline distillation

    v0.5.0 #apple-silicon #mlx #fine-tuning #machine-learning #llm

  48. rlx-lfm

    LiquidAI LFM2.5 runner (text) — LFM SSM LM (decode-step + state wiring)

    v0.2.6 #rlx-models #mlx #runner #lm #ssm #cargo-run #gguf #safetensors #lfm2 #hf

  49. rlx-minimax

    MiniMax M2.5 / M2.7 runner — Lightning Attention LM (decode-step + state buffer wiring)

    v0.2.5 #rlx-models #mlx #lm #runner #minimax #cargo-run #gguf #safetensors #embedding #hf

  50. voice-dsp

    DSP primitives: STFT, iSTFT, overlap-add, windowing

    v0.2.0 #dsp #stft #mlx #windowing #voice #istft #fft #vocoder #hanning #short-time

  51. rlx-neutts

    NeuTTS voice-cloning TTS — GGUF backbone + NeuCodec decoder for RLX

    v0.2.6 #gguf #safetensors #llama #text-to-speech #rlx-models #mlx #voice-cloning #backbone #wgpu #gpu

  52. pmetal-serve

    OpenAI-compatible inference server for PMetal

    v0.5.0 #mlx #apple-silicon #fine-tuning #machine-learning #llm

  53. pmetal-hub

    HuggingFace Hub integration for PMetal

    v0.5.0 #apple-silicon #mlx #fine-tuning #machine-learning #llm

  54. pmetal-data

    Dataset handling and preprocessing for PMetal

    v0.5.0 #llm #fine-tuning #apple-silicon #mlx #machine-learning

  55. rlx-qwen3-tts-train

    RLX MLX/Metal LoRA training for Qwen3-TTS talker (JFK custom voice)

    v0.2.6 #safetensors #mlx #qwen3 #rlx-models #lora #text-to-speech #gguf #cargo-run #talker #hf

  56. rlx-qwen3-tts

    Qwen3-TTS for RLX — talker (Qwen3-shaped) + code predictor + 12Hz codec path

    v0.2.9 #text-to-speech #mlx #inference #wav #talker #qwen3 #predictor #prefill #apple-silicon #progressive

  57. apple-mlx

    Rust bindings and safe wrappers for Apple MLX via the official mlx-c API

    v0.1.1 #mlx #apple-bindings #apple #bindings #ffi #metal

  58. rlx-bonsai

    Bonsai small-reasoning runner — STUB (PLAN.md M4)

    v0.2.6 #gguf #rlx-models #mlx #runner #bonsai #cargo-run #safetensors #m4 #stub #qwen3

  59. rlx-phi

    Phi 3 / Phi 4 runner — STUB (PLAN.md M4)

    v0.2.5 #rlx-models #mlx #runner #phi #md #m4 #cargo-run #gguf #safetensors #stub

  60. rlx-gpt-oss

    gpt-oss-20b runner (delegates to rlx-llama32)

    v0.2.6 #rlx-models #runner #rlx-llama32 #gpt-oss-20b #cargo-run #gguf #safetensors #mlx #qwen3 #cargo-workspace

  61. rlx-nomic

    NomicBERT graph builder for RLX

    v0.2.6 #rlx-models #mlx #builder #graph-builder #gguf #cargo-run #safetensors #apple-silicon #qwen3 #cargo-workspace

  62. rlx-vision

    NomicVision encoder graphs for RLX

    v0.2.6 #safetensors #rlx-models #mlx #encoder #cargo-run #gguf #apple-silicon #qwen3 #embedding #cargo-workspace

  63. rlx-onnx

    ONNX inference for RLX — native compile by default, optional ORT fallback

    v0.2.12 #onnx #mlx #rlx #ort #onnx-inference #cuda #gpu #rocm #ep

  64. rlx-voxtral-tts

    Mistral Voxtral-4B-TTS for RLX — codec decoder + acoustic head (vLLM-Omni port)

    v0.2.9 #safetensors #mlx #rlx-models #text-to-speech #cpu #lm #wgpu #acoustic #prefill #cargo-run

  65. wax-core

    Core inference engine for wax, a small Candle-based local LLM runner

    v0.1.0 #gguf #safetensors #llama #inference-engine #llm #local-llm #llm-inference #mlx #top-p #candle

  66. rlx-cli

    Shared CLI helpers and multiplexer registry for RLX model binaries

    v0.2.9 390 #safetensors #gguf #cargo-run #mlx #qwen3 #rlx-models #text-to-speech #wgpu #model-family #cargo-registry

  67. rlx-fft

    Learned FFT via butterfly networks — train for reference precision, run compiled on RLX backends

    v0.2.9 #fft #inference #mlx #welch #peaks #butterfly #rlx #top-k #rlx-models #spectral

  68. pmetal-vocoder

    Neural vocoder (BigVGAN) for text-to-speech synthesis

    v0.5.0 #mlx #apple-silicon #fine-tuning #machine-learning #llm

  69. rlx-gemma

    Gemma / Gemma 2 causal LMs for RLX

    v0.2.9 #gguf #safetensors #gemma #multimodal #mlx #lm #causal #sliding-window #projector #audio

  70. rlx-onnx-import

    ONNX → RLX HIR import (bundle loader, ONNX protobuf, op lowering)

    v0.2.12 #onnx #safetensors #rlx #hir #bundle #rewrites #downstream #protobuf #mlx #manifest-json

  71. rlx-omnicoder

    OmniCoder Qwen3-coder-shaped runner — STUB (PLAN.md M4)

    v0.2.9 #mlx #rlx-models #inference #text-to-speech #cpu #cuda #wgpu #safetensors #cargo-run #gguf

  72. rlx-granite

    Granite (IBM) Llama-shaped runner — STUB (PLAN.md M4)

    v0.2.9 #mlx #rlx-models #text-to-speech #cpu #inference #cuda #wgpu #safetensors #ibm #cargo-run

  73. rlx-mistral

    Mistral 3+ / Ministral runner — STUB (PLAN.md M4)

    v0.2.9 #mlx #rlx-models #text-to-speech #cpu #inference #mistral #cuda #wgpu #safetensors #cargo-run

  74. rlx-cohere

    Cohere Command-R runner — STUB (PLAN.md M4)

    v0.2.9 #mlx #rlx-models #text-to-speech #cpu #inference #cuda #cohere #wgpu #safetensors #cargo-run

  75. rlx-whisper

    OpenAI Whisper ASR for RLX

    v0.2.9 #mlx #silero-vad #whisper #asr #openai #rlx-models #mel #cuda #safetensors #full-stack

  76. rlx-qwen35

    Qwen3.5 / Qwen3.6 hybrid trunk for RLX

    v0.2.6 #gguf #mlx #trunk #qwen3 #hybrid #moe #llama-cpp #vulkan #mtp #rocm

  77. opf-mlx

    Thin Rust client for the native MLX OpenAI Privacy Filter server

    v0.1.0 #mlx #privacy #redaction #pii #api-bindings

  78. sapient-backends-metal

    Apple MLX / Metal GPU backend for the SAPIENT inference engine (Apple Silicon)

    v0.3.1 #gpu #inference-engine #mlx #sapient #apple-silicon

  79. tsai_cli

    Command-line interface for tsai-rs time series deep learning

    v0.1.2 #deep-learning #forecasting #time-series-transformer #dataset #transformer-model #classification #wgpu #mlx #deep-learning-framework #python-bindings

  80. pmetal-py

    Python bindings for PMetal — high-performance LLM fine-tuning on Apple Silicon

    v0.5.0 #python-bindings #inference #apple-silicon #fine-tuning #lora #p-metal #mlx #llm #model-inference

  81. tsai_data

    Dataset and dataloader implementations for tsai-rs time series deep learning

    v0.1.2 #deep-learning #forecasting #dataset #tsai #classification #data-loader #time-series-transformer #multidimensional-array #mlx #recurrent-neural-network

  82. mlx-sys-burn

    Low-level interface and binding generation for the mlx library (fork with additional operations for burn-mlx)

    v0.2.2 160 #mlx #burn #deep-learning #machine-learning

  83. voice-stt

    Speech-to-text library backed by MLX, starting with Moonshine

    v0.1.0 #text-to-speech #mlx #moonshine #audio-samples #tokenize #hugging-face #cache #transcribe #conv #filesystem-access

  84. rlx-mlx-sys

    Low-level MLX C++ build + C ABI shim for RLX (vendored mlx, NVRTC-free)

    v0.2.12 260 #mlx #rlx #ffi

  85. rlx-nemotron

    NVIDIA Nemotron 3 Nano runner — text + hybrid Mamba2/attention LM

    v0.2.9 #mlx #rlx-models #nvidia #lm #text-to-speech #nvidia-nano #hybrid #cuda #wgpu #nemotron

  86. safemlx-internal-macros

    Internal procedural macros for safemlx

    v0.1.0 #mlx #deep-learning #machine-learning

  87. mlx90640-capture

    Image capture utility for MLX90640 cameras

    v0.1.1 #image-capture #mlx #capture #mlx90640 #melexis

  88. tsai_explain

    Explainability: activation/gradient capture, attribution maps for tsai-rs

    v0.1.2 #forecasting #classification #tsai #transformer-models #attribution #time-series-transformer #gradients #explainability #wgpu #mlx

  89. ftcli

    A command line tool to manage, test and run your 42 projects

    v0.1.4 #test-run #run-command #manage #testing #script #42 #mlx #lint #run-tests #command-line-tool

  90. mlx-autograd

    Automatic differentiation (reverse-mode AD) for MLX tensors

    v0.1.0 #automatic-differentiation #reverse-mode #grad #matmul #vjp #mlx #element-wise

  91. quill-mlx-sys

    Low-level FFI bindings for Apple's MLX machine learning framework

    v0.2.3 #mlx #machine-learning #deep-learning

  92. pmetal-core

    Core types, traits, and configuration for PMetal LLM fine-tuning

    v0.5.0 #mlx #apple-silicon #fine-tuning #machine-learning #llm

  93. mlx-optim

    Optimizers (AdamW, SGD) and learning rate schedulers

    v0.1.0 #optimization #learning-rate #mlx #scheduler #sgd #graph-node

  94. oxidizedmlx-sys

    Unsafe FFI bindings to MLX C API

    v0.1.0 #mlx #tensor #native #bindings #abi #shim

  95. pmetal-mlx-sys

    pmetal-maintained fork of mlx-sys: low-level interface and binding generation for the mlx library

    v0.2.4 #mlx #deep-learning #machine-learning

  96. mlx-ops

    Op registry, broadcasting rules, and dtype promotion for MLX

    v0.1.0 #broadcasting #dtype #rules #registry #promotion #mlx

  97. minilibx

    Rust ffi bindings to the 42 minilibx api for X11 on linux

    v0.2.1 #x11 #mlx #bindings #42 #usr-lib #graphics #beginner #novice #sudo #cp

  98. mlx-cpu

    Pure Rust CPU backend for MLX (correctness oracle)

    v0.1.0 #cpu #back-end #correctness #oracle #reference #mlx #re-exports

  99. mlx-nn

    Neural network modules: Linear, LayerNorm, Attention, etc

    v0.1.0 #neural-network #mlx #layer-norm #module #linear

    100. Try searching with DuckDuckGo.


  100. mlx-conformance

    Golden conformance tests: Rust outputs vs Python MLX oracle

    v0.1.0 #conformance #mlx #python #golden #output

  101. mlx-internal-macros

    Internal procedural macros for mlx-rs

    v0.25.3 #machine-learning #deep-learning #mlx

  102. mlx-macros

    Procedural macros for mlx-rs

    v0.25.3 #machine-learning #deep-learning #mlx

  103. mlx

    Rust port of 42 minilibx

    v0.1.2 #minilibx #42

  104. safemlx-macros

    Procedural macros for safemlx

    v0.1.1 2.6K #mlx #deep-learning #machine-learning

  105. rpmlx90640

    High-level library for imaging using Raspberrypi I2C and the MLX90640 thermal sensor

    v0.1.0 #mlx90640 #thermal #mlx #melexis90640 #melexis

  106. mlx-internal-macros-burn

    Internal procedural macros for mlx-rs-burn

    v0.25.5 #machine-learning #deep-learning #mlx #burn

  107. quill-mlx-internal-macros

    Internal procedural macros for quill-mlx

    v0.25.5 #apple-silicon #machine-learning #deep-learning #mlx

  108. mlx-macros-burn

    Procedural macros for mlx-rs-burn

    v0.25.5 160 #mlx #burn #deep-learning #machine-learning

  109. quill-mlx-macros

    Procedural macros for quill-mlx

    v0.25.5 #apple-silicon #mlx #deep-learning #machine-learning

  110. mlx-lm-rs

    Greenfield Rust port of mlx-lm — Qwen3 inference on Apple Silicon via mlx-rs

    v0.0.1 #llm-inference #apple-silicon #mlx #qwen #llm

  111. mlx-lm

    Rust implementation of mlx-lm

    v0.0.1 #machine-learning #mlx #deep-learning

  112. pmetal-core-derive

    Procedural macros for pmetal-core (JobSpec derive)

    v0.5.0 #apple-silicon #mlx #fine-tuning #machine-learning #llm

  113. mlx-gen

    Rust-native generative image & video model inference on Apple MLX (work in progress; name reserved)

    v0.0.0 #mlx #inference #apple-silicon #generative #diffusion

  114. mlx-lm-utils

    Generic utility functions for mlx-lm

    v0.0.1 #machine-learning #deep-learning #mlx