llamAmpere: llama.cpp fork tuned for RTX 3090

JakeSep 7148 stars

A llama.cpp variant optimised for Ampere cards, reporting very high token rates on 3090 and 3090 Ti, relevant for Flash-Next hosts.

Open on GitHub

Preview of llamAmpere: llama.cpp fork tuned for RTX 3090

Launch: Qwen3.8-Flash-Next
Use case: Local inference
Format: Tool
Source: github.com

Jake

See all

Niko1221

@Niko1221 · Sep 24

Open-source inference engine with an OpenAI/Anthropic-style local API that fits the 125B MoE onto a 12GB consumer GPU plus system RAM. The project behind the model's local-running surge.

David Hendrickson

@TeksEdge · Sep 26

Tells the story of the 12GB RTX 5070 user who wrote Strata after finding llama.cpp too slow.

Alok

@analogalok · Aug 26

Posts a video of the 125B MoE running at about 21 tok/s decode with a quarter-million-token window on one gaming card, no quantised cache.

Unsloth AI

@UnslothAI · Aug 26

Launch-day announcement of GGUF quants and a guide for CPU and unified-memory setups.

Open on GitHub

llamAmpere: llama.cpp fork tuned for RTX 3090

More built with Qwen3.8-Flash-Next