gemma4-26b-a4b 开源项目推荐（7 个）

drumih /turbo-fieldfare

在任何 M 系列 MacBook 上以约 2 GB 内存进行 Gemma 4 26B-A4B 推理

ToddThomson /Mila

A C++23 library for local LLMs at the metal — inference and training, built from explicit neural-network components you can read and understand.

bzcsk2 /covalo

自由优先、模型自适应编码代理运行时，使本地小型大型语言模型能够可靠地运行，支持利用、检查点、验证、缓存感知上下文和自由模型备份。

epsilonagentx /intel_arc_gpu_llm

Docker Compose stack for serving a local, OpenAI-compatible LLM (vLLM on Intel XPU) on an Intel Arc Pro B60 GPU — reproducible config with operator and developer docs.

yan4ikxxx-wq /ExpertGemma

Configuration layer and prompt engineering toolkit for Gemma 4 26B-A4B. Optimized for Google AI Studio.

jon2allen /git_stress_eval

chatdsl for repo evaluation - uses chatybot. ( pip install chatybot )

SourikAdhikary /tracer

Zero-training brand exposure auditor detect any logo in any broadcast using Gemma 4 vision on Apple Silicon