Bigger local AI on the PC you already own. Find models, chat locally, and run supported sparse models across SSD, RAM and NVIDIA GPUs with ESE Studio.
-
Updated
Nov 16, 2026 - C++
Bigger local AI on the PC you already own. Find models, chat locally, and run supported sparse models across SSD, RAM and NVIDIA GPUs with ESE Studio.
Run Kimi K3.1 Pro and DeepSeek V4.1 Flash 1017 locally with Argodrive DS4: NVIDIA CUDA or Apple silicon Metal, NVMe expert streaming, caches and weight preparation. Setup and measured RTX PRO 6000 / M5 Max results included. Based on antirez/ds4; no separate Argodrive app required.
Adaptive MoE inference for Kimi K3 — beyond-memory expert streaming, reversible runtime profiles, measured optimization results, and an open NVIDIA/GPU/NPU adaptation roadmap.
SSD layout, scheduling, benchmarking and monitoring for local mixture-of-experts inference. Argonaut Labs tools for Kimi, DeepSeek and GLM experiments.
Pure-PyTorch DeepSeek-V3/K3-style LLM stack where every serving optimization ships with a bit-exactness oracle: disk-tier expert streaming, KV prefix pool, MTP break-even telemetry, oracle-gated config evolution. 60 tests, all CPU-verified.
Experimental llama.cpp runtime for bounded DeepSeek V4 MoE streaming on dual 16 GB GPUs
To associate your repository with the expert-streaming topic, visit your repo's landing page and select "manage topics."