Classic troll https://t.co/s3PhfDmPw3
— Abhay 🇸🇬🇮🇳 (@Abhay08)
Apr 3, 2026
Author: Abhay Page 5 of 87
BitTorrent meets Napster for LLM inferencing
https://t.co/bgFnO1s870— Abhay 🇸🇬🇮🇳 (@Abhay08)
Apr 3, 2026
RT @hqmank: If you’re using Claude Code, this is worth knowing.
Instead of worrying about whether Opus 4.6 or GPT 5.4 is better, it’s more…
— Abhay 🇸🇬🇮🇳 (@Abhay08)
Apr 3, 2026
@ivanfioravanti Running GLM 5.1 and M2.7 via Ollama Claude code? Global settings won’t work right for 3 separate configs?
— Abhay 🇸🇬🇮🇳 (@Abhay08)
Mar 30, 2026
Implementation of Google’s TurboQuant (ICLR 2026) — KV cache compression for local LLM inference, with planned extensions beyond the paper https://t.co/raO8puxH9B
— Abhay 🇸🇬🇮🇳 (@Abhay08)
Mar 30, 2026
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar https://t.co/ekUuDIqPEI
— Abhay 🇸🇬🇮🇳 (@Abhay08)
Mar 28, 2026
Blown away by first 30m of how Qwen3.5-35B is performing when locally running on my 16gb m4 mini. Swapped my default model for Sun ☀️, 28 Tok/s is excellent! Just go with MoE agent running natively with llama cpp https://t.co/oyoJX1xHiM
— Abhay 🇸🇬🇮🇳 (@Abhay08)
Mar 27, 2026
Excellent read on how Singapore is navigating the current situation https://t.co/QWA0FLG1q9
— Abhay 🇸🇬🇮🇳 (@Abhay08)
Mar 26, 2026