Welcome! Type "help" for available commands.

$

Loading terminal interface...

Experience Education

Projects Bookmarks Investments Contact Blog

Welcome! Type "help" for available commands.

$

Loading terminal interface...

~/bookmarks

Similar Content

A collection of bookmarks filtered by the tag "AI Workloads".

Filter by:

Showing 1-2 of 2 bookmarks tagged with "AI Workloads"

All Stories

Run GPT-OSS-120b with this grammar file to avoid inference issues

Run GPT-OSS-120b with this grammar file to avoid inference issues...

RTX 3090 Intel HX Processors AI Workloads

Feb 14, 2026

$GitHub - fractalbits-labs/fractalbits-main: The ultimate S3 compatible high performance object storage in the AI era.$

GitHub - fractalbits-labs/fractalbits-main: The ultimate S3 compatible high performance object...

S3 Compatible Storage Rust Development AI Workloads

Dec 25, 2025

AI Workloads Bookmarks | William Callahan - Bookmarks

Discover More

localmaxxing.com

May 3, 2026

localmaxxing — Local LLM Inference

localmaxxing — Local LLM Inference

Community-submitted local LLM benchmarks. Compare tok/s, TTFT, and hardware efficiency across GPUs, Apple Silicon, and CPU setups.

Apple Silicon Hardware Comparison LLM Benchmarks Local LLM Inference GPU Performance

LINK

strixhalo-homelab.d7.wtf

September 24, 2025

AI-Capabilities-Overview

AI-Capabilities-Overview

AI Capabilities Overview· WarningThis guide is a work in progress. Also, there has been ongoing progress with software quality and performance so plea...

AI Hardware Platforms Linux Setup Guides GPU Performance Comparisons Local LLM Inference Strix Halo

LINK

github.com

August 19, 2026

GitHub - julianmb/q38rocm: Qwen 3.8 27B ROCmFP4 on AMD Strix Halo (Ryzen AI Max+ 395). Up to 36 tok/s via MTP Speculation, TurboQuant & Mesa RADV Wave64.

GitHub - julianmb/q38rocm: Qwen 3.8 27B ROCmFP4 on AMD Strix Halo (Ryzen AI Max+ 395). Up to 36 tok/s via MTP Speculation, TurboQuant & Mesa RADV Wave64.

Qwen 3.8 27B ROCmFP4 on AMD Strix Halo (Ryzen AI Max+ 395). Up to 36 tok/s via MTP Speculation, TurboQuant & Mesa RADV Wave64. - julianmb/q38rocm

Speculative Decoding AMD Strix Halo ROCmFP4 Qwen 3.8 Local LLM Inference

LINK