Sign inGet started
Repository · GitHub

Lowaltitudeflight/local-llm-tuning-guide

A decision library for running local LLMs on multi-GPU machines without NVLink: parallelism, communication, quantization, speculative decoding, KV cache. Every conclusion carries its evidence grade and reproducible conditions.

OwnerLowaltitudeflight
License (as declared)MIT
Stars19
Forks0
Main languagePython
Created16 October 2026
Last updated at source19 October 2026
pythonbenchmarkingdecision-guidegpu-servinginference-optimizationkv-cachellmllm-deploymentllmopslocal-llmmodel-parallelismmulti-gpunvidianvlinkpcieperformance-tuningquantizationself-hostedspeculative-decodingtensor-parallelismvllm
Embed this entry
<iframe src="https://silytics.si/embed/item/d875eec7-af67-4490-a20b-5b3e4140b734" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Stars, last 5 days

19 now (-2 since 2026-10-19). Counts as reported by the source, snapshotted daily by Silytics.

Silytics shows public metadata from GitHub and links to the original. Information may be incomplete or out of date. Last refreshed 23 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.