#llama.cpp
8
2026-08-29
kadenball/qwen38-27b-rtx3060-dcfr
C
Qwen3.8-27B at 64K on one RTX 3060 12GB: D-CFR llama.cpp research patch and benchmarks
2026-11-08
WWRJ3321/IRIDIS
unrated
IRIDIS is a one-stop Android local AI platform that brings local AI to users' phones faster.
2026-10-16
DingoOz/llm-visuals
unrated
Live truecolor terminal dashboard for a locally running LLM: tok/s, TTFT, GPUs, context, MTP acceptance, layer and real expert routing (llama.cpp)
2026-10-16
JakeATX/llamAmpere
unrated
llama.cpp fork for significantly improved performance on Ampere (especially RTX 3090 / 3090 Ti): example: 95+ tok/s over a 100K-token generation at temperature 1 for qwen3.8, supporting full 262K ctx. Supports low memory (12gb) configs for 200k+ ctx
2026-10-16
stew675/llama-cpp-rdna-boosts
unrated
A set of performant RDNA/HIP patches against llama.cpp focusing on high speed inferencing with numerics assurance
2026-09-29
Show HN: Nibia Fabric – Turn everyday computers into a shared AI compute cluster
unrated
I built NIBIA Fabric, an open-source distributed LLM inference system that pools CPU and RAM across macOS, Linux, and Windows machines. It builds on llama.cpp, with capacity-aware scheduling, adaptive memory reservation, persistent tensor caching, and an OpenAI-compatible API. I’ve validated the current alpha on three physical machines across several models, including a 30B-class Qwen model, as well as GPT-OSS 20B. Feedback on the architecture and use cases is very welcome.
2026-09-03
alphaparkinc/genpark-quantized-model-vram-tensor-parallel-estimator-skill
unrated
Quantized model VRAM footprint & tensor parallelism estimator (llama.cpp)