OSS Radar
Back

PolyStrata alternatives

simplexai-labs/PolyStrata (918 stars, +155 this week): Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith…

Below are 12 other LLM tooling repos tracked by OSS Radar that share at least two GitHub topics about what they do with PolyStrata (platform, language and framework tags don't count), ordered by how closely their topics overlap (rarer shared topics count more), then by stars gained in the last 7 days. Topic overlap means a similar problem space, not a drop-in replacement, so check each project's README.

  1. 1. project-mayamw00/project-maya

    +292/wk

    Run GLM-5.3-Flash (321B), DeepSeek-V4.1-Flash (748B) and MiniMax-M3.1-Flash (428B) on your own GPUs - one engine, one dashboard…

    2.7k stars · Cuda · shared topics: Anthropic API, CUDA, GGUF, GLM, LLM, local LLM, mixture of experts, OpenAI API, self-hosted · project-maya alternatives

  2. 2. kapitsanace-ai/kapitsa

    +208/wkest.

    Blazing fast Apple Silicon inference engine optimized for Qwen & Nemotron. OpenAI + Anthropic API compatible. Built by folks from nace.ai.

    698 stars · C++ · shared topics: local LLM, OpenAI API, Qwen, speculative decoding · kapitsa alternatives

  3. 3. HyperQwensyv-ai/HyperQwen

    +138/wk

    Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM…

    2.6k stars · Python · shared topics: CUDA, local LLM, Qwen, speculative decoding · HyperQwen alternatives

  4. 4. Transformershuggingface/transformers

    +231/wk

    Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models…

    169k stars · Python · shared topics: Gemma, GLM, LLM, Qwen · Transformers alternatives

  5. 5. SGLangsgl-project/sglang

    +228/wk

    SGLang is a high-performance serving framework for large language models and multimodal models.

    39k stars · Python · shared topics: CUDA, GLM, LLM, Qwen · SGLang alternatives

  6. 6. Unslothunslothai/unsloth

    +263/wk

    Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.

    79k stars · Python · shared topics: Gemma, LLM, Qwen, self-hosted · Unsloth alternatives

  7. 7. SoupMakazhanAlpamys/Soup

    +407/wk

    Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

    10k stars · Python · shared topics: GGUF, LLM, local LLM · Soup alternatives

  8. 8. vLLMvllm-project/vllm

    +464/wk

    A high-throughput and memory-efficient inference and serving engine for LLMs.

    97k stars · Python · shared topics: CUDA, LLM, Qwen · vLLM alternatives

  9. 9. ai-infra-bookbojieli/ai-infra-book

    +160/wk

    Open-source book that derives LLM inference and training system design from hardware limits, with calculation tools.

    7.4k stars · Python · shared topics: LLM, mixture of experts · ai-infra-book alternatives

  10. 10. mojo-dllmvladimirrott/mojo-dllm

    +244/wkest.

    Local inference for diffusion language models (LLaDA, Dream), written in Mojo.

    457 stars · Mojo · shared topics: GGUF, LLM · mojo-dllm alternatives

  11. 11. llmfitAlexsJones/llmfit

    +212/wk

    Hundreds of models & providers. One command to find what runs on your hardware.

    39k stars · Rust · shared topics: GGUF, LLM · llmfit alternatives

  12. 12. omlxjundot/omlx

    +184/wk

    LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar.

    23k stars · Python · shared topics: LLM, OpenAI API · omlx alternatives

More: all trending LLM tooling repos · trending LLM repos · trending Qwen repos · trending self-hosted repos · compare PolyStrata with the top 2 · alternatives to other trending repos