Artificial Intelligence

Machine Learning

Turbo Quant

Explore recommended reads, summarized by AI

Running Large Models Locally

Techniques and tools for running large language models on consumer hardware with limited resources.

TurboQuant Compression Techniques

Popular this week

In

Data Science Collective

by

Manjunath Janardhan

Qwen 3.8–27B on a 16 GB Mac mini: Alibaba’s new vision model, fully in memory

In

Data Science Collective

by

Manjunath Janardhan

A Qwen 3.5 122B LLM on a 16 GB Mac mini: MoE Expert Streaming with TurboQuant-MLX

Rajveer Rathod

Stop Losing 80% of Your Mac’s Memory to LLM Inference. Here’s How.

Lentigrams

Squeeze the most out of Qwen 3.6

Mohamed Arbi Nsibi

Qdrant 1.20: BM25 Without Sparse Vectors, Turbo16 & Turbo8

Latest stories

Mohamed Arbi Nsibi

Qdrant 1.20: BM25 Without Sparse Vectors, Turbo16 & Turbo8

In

Data Science Collective

by

Manjunath Janardhan

I Measured Prism ML’s Bonsai 2 Against My Own Builds of Alibaba’s Qwen3.8–27B.

In

Data Science Collective

by

Manjunath Janardhan

Muse Glimmer on a 16 GB Mac mini: the 5 GB your 4-bit build never compressed

Mohamed Arbi Nsibi

Qdrant 1.19: Turbo4 Datatype & Memory Tiers

DhanushKumar

TurboVec and TurboQuant: How 10 Million Vectors Can Fit in a Few Gigabytes

See more stories

Who to follow

Popular this week

In

Data Science Collective

by

Manjunath Janardhan

Qwen 3.8–27B on a 16 GB Mac mini: Alibaba’s new vision model, fully in memory

In

Data Science Collective

by

Manjunath Janardhan

A Qwen 3.5 122B LLM on a 16 GB Mac mini: MoE Expert Streaming with TurboQuant-MLX

Rajveer Rathod

Stop Losing 80% of Your Mac’s Memory to LLM Inference. Here’s How.

Lentigrams

Squeeze the most out of Qwen 3.6

Mohamed Arbi Nsibi

Qdrant 1.20: BM25 Without Sparse Vectors, Turbo16 & Turbo8

Latest stories

Mohamed Arbi Nsibi

Qdrant 1.20: BM25 Without Sparse Vectors, Turbo16 & Turbo8

In

Data Science Collective

by

Manjunath Janardhan

I Measured Prism ML’s Bonsai 2 Against My Own Builds of Alibaba’s Qwen3.8–27B.

In

Data Science Collective

by

Manjunath Janardhan

Muse Glimmer on a 16 GB Mac mini: the 5 GB your 4-bit build never compressed

Mohamed Arbi Nsibi

Qdrant 1.19: Turbo4 Datatype & Memory Tiers

DhanushKumar

TurboVec and TurboQuant: How 10 Million Vectors Can Fit in a Few Gigabytes

See more stories

Who to follow