Local LLM Index / local
← All tools
The Local LLM Index / On-Device & Mobile / #13

drumih/turbo-fieldfare

by drumih · On-Device & Mobile · updated today

Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook

77
momentum
7,062
stars
456
forks
#13
rank
apple-silicongemmagemma4gemma4-26b-a4bgpgpullmllm-inferencelocal-aimacosmetalon-device-aion-device-llm
View on GitHub →

More in On-Device & Mobile

On-Device & Mobile#6
MNN
MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-
On-Device & Mobile#9
needle
Automation foundation model for tiny devices: 2-bit, 8-29 MB, tool calls, ASR, structured
On-Device & Mobile#10
runanywhere-sdks
Production ready toolkit to run AI locally
On-Device & Mobile#14
GenieX
Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few