safetensors repositories

Trending repositories tagged safetensors, ranked by trending score. Updated daily.

  1. 1
    qybaihe/bla

    ๐Ÿ›ก๏ธ BLA (bla-agents / Blind LLM Agents) โ€” Open-source Blue Defense MCP server & CLI protecting JS/TS, Electron ASAR, WASM, Python, Native Binaries, SQLite, GGUF/Safetensors & Android DEX against AI reverse-engineering agents (REA).

    GitHub ยท TypeScript ยท 6,369 stars ยท 788 forks ยท +188 stars in 24 hours ยท Trending score 4.49

  2. 2
    lutzroeder/netron

    Visualizer for neural network, deep learning and machine learning models

    GitHub ยท JavaScript ยท 33,715 stars ยท 3,200 forks ยท +13 stars in 24 hours ยท Trending score 2.26

  3. 3
    gwenn-ha-dev/Siliconed

    Local image generation and editing on Apple silicon, built on Core AI. Krea 2, Z-Image, Qwen-Image 2.1, Anima and MOSS-Image in native Swift, on the GPU and the Neural Engine, under a fixed memory budget. No Python, no cloud.

    GitHub ยท Swift ยท 35 stars ยท 2 forks ยท +11 stars in 24 hours ยท Trending score 1.75

  4. 4
    glimapp/glim

    A free, open-source file viewer for macOS.

    GitHub ยท Rust ยท 47 stars ยท 7 forks ยท +2 stars in 24 hours ยท Trending score 1.05

  5. 5
    TSPstudio/kotensor

    Train, fine-tune and run Transformer LLMs in pure Kotlin on the JVM and Android โ€” no native code.

    GitHub ยท Kotlin ยท 14 stars ยท 0 forks ยท +1 stars in 24 hours ยท Trending score 0.72

  6. 6
    Ton-Llop/Jaull

    Find LLMs that fit your hardware and validate them with reproducible local tests.

    GitHub ยท Python ยท 15 stars ยท 1 forks ยท 0 stars in 24 hours ยท Trending score 0.56

  7. 7
    alvarobartt/hf-mem

    A CLI to estimate inference memory requirements for Hugging Face models, written in Python.

    GitHub ยท Python ยท 956 stars ยท 85 forks ยท 0 stars in 24 hours ยท Trending score 0.56

  8. 8
    LostBeard/SpawnDev.ILGPU.ML

    Hardware-agnostic machine learning infrastructure for .NET. Implements high-performance neural network layers in C# that are transpiled to run on WebGPU, CUDA, OpenCL, WebGL, CPU, and Wasm via SpawnDev.ILGPU. Optimized for Blazor WebAssembly and native GPU execution.

    GitHub ยท C# ยท 26 stars ยท 4 forks ยท +1 stars in 24 hours ยท Trending score 0.55

  9. 9
    SunDoge/dlpark

    Pure Rust DLPack implementation for zero-copy tensor interoperability

    GitHub ยท Rust ยท 67 stars ยท 5 forks ยท +1 stars in 24 hours ยท Trending score 0.54

  10. 10
    DA3M0/Cheetah

    A single-binary local LLM inference server in Rust + C. Supports Safetensors (F32/F16/BF16) CPU/Vulkan. OpenAI-compatible gateway

    GitHub ยท Rust ยท 21 stars ยท 2 forks ยท +1 stars in 24 hours ยท Trending score 0.41

  11. 11
    ruvnet/ruv-FANN

    Neural networks and weight-space programming in Rust, JavaScript and WebAssembly. Inspect activations, edit weights, evaluate candidates, train small models, and explicitly promote or roll back revisions.

    GitHub ยท Rust ยท 394 stars ยท 109 forks ยท 0 stars in 24 hours ยท Trending score 0.35

  12. 12
    shootthesound/comfyui-model-diff-to-lora

    Extract a LoRA from the difference between two MODEL objects in ComfyUI. Capture chained edits (LoRAs, layer scaling, merges, IP-Adapter, patches) as a single distributable .safetensors file.

    GitHub ยท Python ยท 12 stars ยท 2 forks ยท 0 stars in 24 hours ยท Trending score 0.22

  13. 13
    CH-Abhinav/JNum

    Java numerations - a library which has various numerical analysis (High-performance pure Java 25 & Kotlin numerical computing and tensor library powered by Project Panama (FFM & Vector API))

    GitHub ยท Java ยท 35 stars ยท 0 forks ยท 0 stars in 24 hours ยท Trending score 0.22

  14. 14
    Miyamoto-Renya/LaplacesScissors

    Laplace's Scissors: protected readout rotations for open LLMs. Diagnose weak output directions, repair answers, preserve successful generations, and analyze scaling deviations with Rust and Triton on CUDA/HIP.

    GitHub ยท Rust ยท 33 stars ยท 8 forks ยท 0 stars in 24 hours ยท Trending score 0.15

  15. 15
    shootthesound/tensorvillage

    One organized drive for every AI model you own - however many disks they are scattered across. Windows.

    GitHub ยท 11 stars ยท 1 forks ยท 0 stars in 24 hours ยท Trending score 0.14

  16. 16
    ruvnet/ruvllm

    Governed neural weight editing and coding model adaptation. Native Rust patches, exact rollback, LoRA, Claude Code routing, and reproducible benchmarks.

    GitHub ยท Python ยท 15 stars ยท 1 forks ยท 0 stars in 24 hours ยท Trending score 0.14

  17. 17
    townsendmerino/goinfer

    Pure-Go, no-cgo local LLM inference โ€” run Gemma, Qwen, Llama and friends from safetensors or GGUF in a single static binary.

    GitHub ยท Go ยท 26 stars ยท 7 forks ยท 0 stars in 24 hours ยท Trending score 0.10

  18. 18
    kekzl/imp

    Run large AI chat models privately on your own NVIDIA RTX 50 or RTX PRO graphics card. On one RTX 5090, Qwen3.8-27B writes about 70 words per second, 1.4x faster than vLLM. Even a model almost four times larger than the card's memory runs. Works with apps made for ChatGPT or Claude. Starts with one docker command.

    GitHub ยท C++ ยท 79 stars ยท 6 forks ยท โˆ’4 stars in 24 hours ยท Trending score 0.09

  19. 19
    xquantize/eqx-zoo

    Verified JAX/Equinox ports of Hugging Face LLMs and embedding models: numerically matched against PyTorch, forward and backward, and saved back to Hugging Face formats.

    GitHub ยท Python ยท 7 stars ยท 0 forks ยท 0 stars in 24 hours ยท Trending score 0.08

  20. 20
    av/harbor

    Stop configuring your AI stack. Start using it. One command brings a complete pre-wired LLM stack with hundreds of services to explore.

    GitHub ยท Python ยท 3,269 stars ยท 237 forks ยท 0 stars in 24 hours ยท Trending score 0.03

  21. 21
    outerreaches/moonshine

    Run the official Kimi K3 MoE checkpoint on one 128 GB AMD Strix Halo box. ROCm-resident static weights, MXFP4 experts streamed from NVMe via io_uring. C engine, chat client, OpenAI-compatible server. Very experimental.

    GitHub ยท C ยท 7 stars ยท 0 forks ยท 0 stars in 24 hours ยท Trending score 0.00

  22. 22
    foundation-model-stack/fastsafetensors

    High-performance safetensors model loader

    GitHub ยท Python ยท 185 stars ยท 43 forks ยท 0 stars in 24 hours ยท Trending score 0.00

  23. 23
    qskousen/ggufy

    CLI/GUI tool for efficient and easy safetensors and gguf model conversion

    GitHub ยท Zig ยท 111 stars ยท 10 forks ยท 0 stars in 24 hours ยท Trending score 0.00

  24. 24
    barrontang/gguf2mlx

    Convert GGUF models into MLX-LM and mlx-vlm directories: adapter-based, fail-closed, no silent precision loss.

    GitHub ยท Python ยท 49 stars ยท 7 forks ยท 0 stars in 24 hours ยท Trending score 0.00