OSS Radar
Back

Xolotl alternatives

Indras-Mirror/Xolotl (50 stars, +175 this week): Xolotl (formerly Strata-DSV4.1): DeepSeek-V4.1-Flash, all 552B, on one gaming PC (RTX 4090 + 90 GB RAM) at ~27 tok/s, plus GLM-5.3-Flash… Why it matters: useful plumbing for shipping LLM-powered features.

Below are 12 other LLM tooling repos tracked by OSS Radar that share at least two GitHub topics with Xolotl, ordered by how many topics overlap, 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. mw00/project-maya

    +380/wkest.

    Project Maya - run GLM-5.3-Flash (321B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Why it matters: useful plumbing for shipping LLM-powered features.

    1k stars · C++ · shared topics: cuda, glm, llm-inference, local-llm, mixture-of-experts, moe · project-maya alternatives

  2. 2. VecSzn/PolyStrata

    +182/wkest.

    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… Why it matters: useful plumbing for shipping LLM-powered features.

    190 stars · C++ · shared topics: cuda, gguf, glm, local-llm, mixture-of-experts, qwen · PolyStrata alternatives

  3. 3. sgl-project/sglang

    +277/wkest.

    SGLang is a high-performance serving framework for large language models and multimodal models. Why it matters: useful plumbing for shipping LLM-powered features.

    37k stars · Python · shared topics: cuda, deepseek, glm, moe, qwen · sglang alternatives

  4. 4. vllm-project/vllm

    +480/wkest.

    A high-throughput and memory-efficient inference and serving engine for LLMs. Why it matters: useful plumbing for shipping LLM-powered features.

    94k stars · Python · shared topics: cuda, deepseek, moe, qwen · vllm alternatives

  5. 5. FlashML-org/FreeToken

    +147/wkest.

    FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently. Why it matters: useful plumbing for shipping LLM-powered features.

    15k stars · Python · shared topics: deepseek-v4, glm, moe, qwen · FreeToken alternatives

  6. 6. ollama/ollama

    +1k/wkest.

    Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. Why it matters: useful plumbing for shipping LLM-powered features.

    184k stars · Go · shared topics: deepseek, glm, qwen · ollama alternatives

  7. 7. bojieli/ai-infra-book

    +403/wkest.

    Open-source book that derives LLM inference and training system design from hardware limits, with calculation tools. Why it matters: useful plumbing for shipping LLM-powered features.

    6.7k stars · Python · shared topics: deepseek, llm-inference, mixture-of-experts · ai-infra-book alternatives

  8. 8. huggingface/transformers

    +201/wkest.

    🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models… Why it matters: useful plumbing for shipping LLM-powered features.

    168k stars · Python · shared topics: deepseek, glm, qwen · transformers alternatives

  9. 9. diegosouzapw/OmniRoute

    +2.7k/wkest.

    Never stop coding. Free MIT AI gateway: one endpoint, 359 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek… Why it matters: useful plumbing for shipping LLM-powered features.

    78k stars · TypeScript · shared topics: deepseek, qwen · OmniRoute alternatives

  10. 10. MakazhanAlpamys/Soup

    +691/wkest.

    Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU. Why it matters: useful plumbing for shipping LLM-powered features.

    9.3k stars · Python · shared topics: gguf, local-llm · Soup alternatives

  11. 11. unslothai/unsloth

    +418/wkest.

    Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more. Why it matters: useful plumbing for shipping LLM-powered features.

    78k stars · Python · shared topics: deepseek, qwen · unsloth alternatives

  12. 12. decolua/9router

    +383/wkest.

    Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. Why it matters: useful plumbing for shipping LLM-powered features.

    31k stars · JavaScript · shared topics: deepseek, qwen · 9router alternatives

More: all trending LLM tooling repos · compare Xolotl with the top 2 · alternatives to other trending repos