Filter

Clear Filter

Archived Not Archived

Forked Not Forked

Mirrored Not Mirrored

Template Not Template

Private Public

Sort

Newest Oldest Alphabetically Reverse alphabetically Most recently updated Least recently updated Most stars Fewest stars Most forks Fewest forks Smallest size Largest size

Yamz-Labs/ kyojin

Python 0 0 0

Kyojin: open-source engine that runs 100 GB-class open models (GLM-5.3, Qwen3.8, DeepSeek V4.1) on one desktop machine. AMD Strix Halo, NVIDIA RTX and Apple Mac. OpenAI API, built on ExLlamaV3.

amd apple-silicon cuda deepseek exl3 exllamav3 glm inference llm llm-inference local-llm nvidia openai-api quantization qwen rocm strix-halo

Updated 2026-11-07 01:15:32 -10:00

yindo/ kyojin

Python 0 0 0

Kyojin: open-source engine that runs the largest open models on one mini PC or one graphics card, about 2× faster than llama.cpp. AMD (ROCm) and NVIDIA (CUDA), built on ExLlamaV3.

Updated 2026-10-30 01:04:05 -09:00

Heretek-AI/ lucebox-BUILDER

Python 0 0 0

⚡ Automated nightly builds & portable releases for lucebox (DFlash) inference server on NVIDIA CUDA (sm_75-120) and AMD ROCm 7 (Strix Halo gfx1151, RX 7900 XTX gfx1100, R9700 gfx1201) with zero-dependency $ORIGIN RPATH bundling.

ai-inference cuda deepseek-v3 deepseek-v4 dflash gfx1100 gfx1151 gfx1201 hip llm-inference lucebox nightly-builds portable-binaries rdna3 rdna4 rocm rocm-7 rtx5090 rx7900xtx strix-halo

Updated 2026-08-30 16:02:00 -09:00