Mia's AI Lab

No description.

Deploy DeepSeek V4 Flash (MoE reasoning model) on dual DGX Spark nodes with 1M token context, InfiniBand, and FP8 KV-cache

Production-ready vLLM deployment wrapper for Qwen3.6-27B (NVFP4) — self-hosted OpenAI-compatible inference

Head-to-head comparison of local LLMs for agentic workflows (Hermes Agent, tool-eval-bench)

Self-hosted vLLM inference for Qwen3.6-35B-A3B-NVFP4

Setup wizard for Hermes Gateway Desktop

llama-server start/stop scripts for Qwen3.6-35B-A3B UD-Q8_K_XL GGUF on DGX Spark

vLLM deployment for Unsloth Qwen3.6-35B-A3B-NVFP4-Fast on NVIDIA DGX Spark

DeepSeek V4 Flash DSpark Abliterated (Uncensored) — 2× DGX Spark serving

No description.

tool-eval-bench results for Prism ML Ternary-Bonsai-27B (Q2_0) — 8 trials, score 85, deployability 80

Mia's MiMo-V2.5 Dual DGX Spark start script — Omni MTP1 + NVFP4-KV TP=2 on 2× GB10

Gemma 4 26B vLLM launch scripts for DGX Spark concurrency testing

tool-eval-bench: Qwen3.6-27B GGUF Q8_K_XL vs NVIDIA NVFP4 — head-to-head tool-calling quality comparison

Head-to-head comparison of DeepSeek-V4-Flash vs Step-3.7-Flash on tool-eval-bench v2.0.6 (69 scenarios). Full results, summary, and analysis.

Tool evaluation benchmarks comparing Qwen3.6-35B vs DeepSeek V4 Flash DSpark

Independent evaluation of Mistral Leanstral-1.5 for Lean 4 formal proof engineering

Hy3-295B NVFP4 serving on 2x DGX Spark (TP=2, Ray, vLLM)

Serve NVIDIA Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4 on a single DGX Spark (GB10) node with vLLM 0.24 in Docker

No description.

Serve nvidia/Gemma-4-31B-IT-NVFP4 via vLLM with MTP speculative decoding, tool calling, and thinking/reasoning support

Tool-calling quality benchmark for LLM serving stacks. 80+ deterministic scenarios testing multi-turn orchestration, safety boundaries, and structured output. Supports vLLM, SGLang, and llama.cpp.

Head-to-head tool-eval-bench comparison: Laguna-XS-2.1-Q8_0 vs Qwen3.6-35B-A3B-UD-Q8_K_XL

A fast, light-weight OLED-friendly MD/text editor.

Tool-eval-bench comparison: Agents-A1-Q8_0.gguf vs Qwen3.6-35B-A3B-UD-Q8_K_XL

No description.

No description.

No description.

No description.

SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.

Head-to-head tool-eval-bench comparison: Qwen3.6-35B vs Qwen-AgentWorld-35B

Discover and mount external USB storage devices automatically.

Tool-call benchmark comparison: DeepSeek-V4-Flash with Thinking ON vs Thinking OFF (tool-eval-bench, vLLM)

RepoPrompt for Windows — Context Engineering Tool for AI Coding Agents. Windows port of repoprompt/repoprompt-ce.

A curated list of 100+ awesome note-taking apps, PKM tools & knowledge management software — open source and proprietary. Updated regularly.

A collection of awesome markdown editors & (pre)viewers for Linux, Apple OS X, Microsoft Windows, the World Wide Web & more

An awesome & curated list of tools and apps for Windows 10/11.

Awesome Privacy - A curated list of services and alternatives that respect your privacy because PRIVACY MATTERS.

:memo: Delightful Markdown stuff.

⚡ A curated list of awesome Svelte resources

A curated list of Rust code and resources.

🚀 Awesome Tauri Apps, Plugins and Resources

A lightweight, self-hosted wiki for managing, organizing, and reusing LLM prompts