Open-source engine enables local execution of Gemma 4 26B on any M-series Mac with just 2GB of memory

Open-source engine enables local execution of Gemma 4 26B on any M-series Mac with just 2GB of memory

2026-07-29 16:40View Original

According to the project page, an open-source engine has been released on GitHub, enabling the Gemma 4 26B model to run on any M-series Mac with as little as 2GB of memory required. Targeting local large language model deployment scenarios, this project focuses on reducing dependency on high-memory devices and specialized hardware, allowing M-series Mac users to deploy 26B-parameter-scale models natively. In contrast to typical large models requiring higher memory configurations for local inference, the core innovation of this engine lies in lowering resource barriers and opening access and validation to developers through open-source distribution.

Disclaimer: Contains third-party opinions, does not constitute financial advice

Recommended Reading

Tencent Hunyuan team open-sources the speculative decoding framework AngelSpec, and releases drafter weights and training code for Hy3-A21B

2 hours ago
Tencent Hunyuan team open-sources the speculative decoding framework AngelSpec, and releases drafter weights and training code for Hy3-A21B

NVIDIA fell 5% on Monday, during which retail investors bought $108 million, marking the weakest accumulation since early 2025.

2 hours ago
NVIDIA fell 5% on Monday, during which retail investors bought $108 million, marking the weakest accumulation since early 2025.

Perplexity's open-source agent detection and response layer, Numbat, blocks selected actions before execution

2 hours ago
Perplexity's open-source agent detection and response layer, Numbat, blocks selected actions before execution

SK hynix reports strong chip demand in Q2, with AI and memory stocks rebounding pre-market on Wednesday

10 hours ago
SK hynix reports strong chip demand in Q2, with AI and memory stocks rebounding pre-market on Wednesday

South Korean President Yoon Suk-yeol hosts a dinner in San Francisco for executives from NVIDIA, Broadcom, Microsoft, and South Korean technology firms

2 days ago
South Korean President Yoon Suk-yeol hosts a dinner in San Francisco for executives from NVIDIA, Broadcom, Microsoft, and South Korean technology firms

OpenRouter July 26, 2026 LLM Token Usage Rankings: MiMo V2.5, DeepSeek V4 Flash, Hy3 Rank in Top Three

2 days ago
OpenRouter July 26, 2026 LLM Token Usage Rankings: MiMo V2.5, DeepSeek V4 Flash, Hy3 Rank in Top Three

OpenAI and Microsoft Update Their Partnership, Gaining the Right to Deploy Products and Services Across All Cloud Platforms

4 days ago
OpenAI and Microsoft Update Their Partnership, Gaining the Right to Deploy Products and Services Across All Cloud Platforms