Dual-engine (llama.cpp + vLLM) LLM benchmarking pipeline for GGUF & safetensors on NVIDIA GPUs — speed, quality, live dashboard, publishable cards.
☆48Nov 12, 2026Updated this week
Alternatives and similar repositories for llm-bench-rig
Users that are interested in llm-bench-rig are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Easily run LLMs locally using llama.cpp directly, without overhead.☆21Aug 15, 2026Updated 3 months ago
- ☆31Updated this week
- SparkPilot puts your NVIDIA DGX Spark to work, free forever.☆16Sep 11, 2026Updated 2 months ago
- Reproducible recipe: serve abliterated Gemma-4-12B (gemma4_unified) at 50-118 tok/s on no-NVLink Blackwell (SM120) via vLLM nightly + Mod…☆14Jun 7, 2026Updated 5 months ago
- Live OSINT globe for Hermes Desktop: earthquakes, disasters, aircraft, satellites, news incidents, recon and agent briefings from public …☆33Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Nous Research's experimental LLM story generator☆12Mar 19, 2025Updated last year
- Raw speed benchmark traces: Qwen3.8-27B on 4x RTX 3090. llama.cpp GGUF sweeps + 288-point vLLM vs SGLang, NVFP4 vs FP8 matrix.☆14Sep 28, 2026Updated last month
- REAP expert pruning for MoE LLMs on Apple Silicon via MLX☆58Mar 16, 2026Updated 7 months ago
- A streaming Mixture-of-Experts (MoE) inference engine written in pure C, that runs models larger than your RAM on ordinary consumer hardw…☆11Updated this week
- Qwen3.8-27B ADay777-Ablit · NVFP4 · A4Q · NVFP4-KV (4M+ pool) · MTP-3 — single DGX Spark (GB10/sm121), eugr vLLM 0.27. 1M ctx @ c=4.☆24Aug 17, 2026Updated 2 months ago
- ☆17Aug 16, 2026Updated 2 months ago
- A set of PSScriptAnalyzer rules that help make it Good Enough!☆11Aug 26, 2026Updated 2 months ago
- ☆11Jul 10, 2026Updated 4 months ago
- Autonomous self-improving 4x DGX Spark (GB10) MoA stack + LoRA loop (DSV4F router, Qwen3.6/Omni/TwoTower/Gemma). Hermes MoA routing, ~90%…☆24Aug 17, 2026Updated 2 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- A Prometheus metrics exporter for NVIDIA DGX Spark clusters.☆26Feb 16, 2026Updated 8 months ago
- Meta-research lab for domain chip R&D, methodology improvement, and recursive self-improvement☆22Jul 26, 2026Updated 3 months ago
- Open quantization tooling for TurboQuant-style low-bit LLM releases, stock GGUF deployment, and Apple Silicon runtime experiments.☆10May 5, 2026Updated 6 months ago
- Lightweight graph authentication, get security tokens (access/refresh) directly from the protocol by authorization code with PKCE, client…☆10Feb 6, 2023Updated 3 years ago
- Strata engine support for Gyro-M on 12 GB VRAM and 32 GB RAM☆16Oct 20, 2026Updated 3 weeks ago
- Uncensored/abliterated Ornith-1.0-35B (AEON Ultimate): 0% refusal, 0 coding-capability loss. BF16 + FP8 for vLLM.☆89Updated this week
- Paste, and drag drop images to load them into Pi. Also works in tmux.☆12May 5, 2026Updated 6 months ago
- A magical package manager written in elixir☆12Aug 13, 2025Updated last year
- A platform to take building Identity Security Cloud integrations to a whole new level☆15Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆22Oct 18, 2026Updated 3 weeks ago
- Serve the home! Inference stack for your Nvidia DGX / RTX Spark (128GB ram) aka the Grace Blackwell AI supercomputer on your desk. Mostly…☆52Oct 11, 2026Updated last month
- Running MiniMax-M2.5 on a Nvidia DGX Spark with OpenCode on the remote machine☆12Feb 19, 2026Updated 8 months ago
- Tool-calling quality benchmark for LLM serving stacks. 80+ deterministic scenarios testing multi-turn orchestration, safety boundaries, a…☆427Updated this week
- This one, you can unmute: a camera flies over a DAW timeline in one shot while a tracker locks onto every beat. Music composed in code, e…☆32Oct 22, 2026Updated 3 weeks ago
- ☆11Jun 16, 2026Updated 4 months ago
- FireRedTTS3 for ComfyUI: multilingual zero-shot voice cloning, voice design, speech editing, Whisper transcripts, AIMDO DynamicVRAM, with…☆23Aug 18, 2026Updated 2 months ago
- Self-hosted live telemetry, alerts and benchmarks for NVIDIA DGX Spark (GB10) clusters☆12Updated this week
- A crawler to export all chat threads in a Microsoft Teams channel☆12Feb 16, 2021Updated 5 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Contains code from the PowerShell Pro Tips series.☆14Apr 23, 2025Updated last year
- Skill for collaborative agent work in herdr. One agent presents, the others critique, you adjudicate.☆20Oct 14, 2026Updated last month
- Hermes Agent proficiencies: shareable operating-attribute skills for human SOPs/playbooks, agent skill/tool-SOP building, safe publishing…☆34Jul 13, 2026Updated 4 months ago
- A collection of strategy games and bots which seek to play them well.☆11May 18, 2024Updated 2 years ago
- [Archived as unmaintained 2023-07-31] InvokeBuild is a great project that has improved my development workflow tremendously. Highly recom…☆13Jun 28, 2026Updated 4 months ago
- Head-to-head comparison of local LLMs for agentic workflows (Hermes Agent, tool-eval-bench)☆36Oct 4, 2026Updated last month
- Az összes iskolai feladat amit kiadtak nekünk...☆18Updated this week
Are these results useful?