#

ik-llama-cpp

Here are 7 public repositories matching this topic...

5p00kyy / club-5060ti

Practical local LLM recipes and benchmarks for RTX 5060 Ti setups

benchmark cuda nvidia blackwell llama-cpp vllm qwen ik-llama-cpp

Updated Sep 16, 2026
Python

raketenkater / opencode-dcp-dynamic-limits

opencode dcp llama-cpp local-llm context-window gguf llm-server opencode-plugin ik-llama-cpp

Updated May 27, 2026
TypeScript

midagedev / rig-log

A build log for one workstation: a 284B mixture-of-experts model across two GPUs and 256 GB of RAM, measured.

threadripper mixture-of-experts llama-cpp local-llm gguf speculative-decoding deepseek ik-llama-cpp moe-offloading

Updated Sep 17, 2026
Shell

Aulora137 / Lean_llama.cpp

Turboquant Q4/Q3 with IQK FA

quantization kv-cache llm llama-cpp ik-llama-cpp turboquant

Updated Jul 22, 2026
C++

Aulora137 / LeanKV

Turboquant Q4/Q3 with IQK FA

quantization kv-cache llm llama-cpp ik-llama-cpp turboquant

Updated Apr 19, 2026
Python

xautonomics-inc / dreamcatcher

llama.cpp based distributed MoE inference platform for mixed architecture clusters

vulkan cuda moe mixture-of-experts llama-cpp llm-inference gguf distributed-inference ik-llama-cpp

Updated Sep 17, 2026
C++

daimonionnn / ik-llama-toolkit

A one-command inference server and benchmark harness for running large language models that don't fit in your GPU's VRAM. Optimized for RTX PRO 6000 and Deepseek v4 flash

cuda nvidia rtx llm llama-cpp deepseek mxfp4 rtx-pro-6000 rtx-6000 deepseek-v4 ik-llama-cpp deepseek-v4-flash qwen3-8-flash-next

Updated Sep 14, 2026
Shell

Add this topic to your repo

To associate your repository with the ik-llama-cpp topic, visit your repo's landing page and select "manage topics."