Reproducible recipe: serve abliterated Gemma-4-12B (gemma4_unified) at 50-118 tok/s on no-NVLink Blackwell (SM120) via vLLM nightly + ModelOpt FP8/NVFP4 + MTP spec-decode.
☆14Jun 7, 2026Updated 5 months ago
Alternatives and similar repositories for gemma4-12b-vllm-sm120
Users that are interested in gemma4-12b-vllm-sm120 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Codes for A Simple Yet Strong Baseline for Long-Term Conversational Memory of LLM Agents☆17Jan 17, 2026Updated 9 months ago
- Experimental Normalized Attention Guidance node for Anima in ComfyUI.☆14Oct 18, 2026Updated 3 weeks ago
- Murder the slop, not the codebase.☆12Jul 28, 2026Updated 3 months ago
- ☆11Jul 10, 2026Updated 4 months ago
- JanusPro ComfyUI plugin☆12Feb 8, 2025Updated last year
- 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.
- Qwen-Image-2.1をRTX4070 12GBで動かした備忘録/DeepSeekちゃんのデモワークフロー付き🐳☆17Sep 24, 2026Updated last month
- A React and Vite-based tool with an Express backend that converts text, screenshots, and Figma designs into clean, functional code powere…☆16Sep 11, 2024Updated 2 years ago
- Mac/Linux driver for the Orion StarShoot Autoguider☆10Sep 21, 2012Updated 14 years ago
- ☆21Aug 6, 2026Updated 3 months ago
- A Home Assistant custom component for UK Government Fuel Finder API, monitor fuel prices at nearby petrol stations☆18Nov 5, 2026Updated last week
- ☆24Sep 5, 2024Updated 2 years ago
- With this tool you can create custom TTS dataset from video or audio.☆18Jun 7, 2025Updated last year
- react native实现Android,Ios,Web万年历☆10Apr 22, 2025Updated last year
- ☆18Sep 3, 2023Updated 3 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Dual-engine (llama.cpp + vLLM) LLM benchmarking pipeline for GGUF & safetensors on NVIDIA GPUs — speed, quality, live dashboard, publisha…☆48Updated this week
- NVFP4 KV cache for vLLM on SM120 (RTX PRO 6000) via FlashInfer FA2 explicit-SF-stride patch — ~1.5x fp8 pool at ~95-104% speed☆20Jun 5, 2026Updated 5 months ago
- ComfyUI-KokoroTTS: A text-to-speech model that utilizes the Kokoro TTS framework to convert text into natural-sounding speech. It suppor…☆13Apr 18, 2025Updated last year
- NVFP4 Gemma-4 26B-A4B MoE for DGX Spark — optimal recipe: DFlash n=10 (flex) on AEON vLLM Ultimate. 144 tok/s single / 1,724 peak (Coding…☆46Updated this week
- Abstract Syntax Trees Evaluated Restricted Run (ASTERR) is a Python Script executor for ComfyUI☆30Oct 27, 2024Updated 2 years ago
- SDXL LoRA Factory is a GUI tool designed to make Stable Diffusion XL (SDXL) LoRA training easy and intuitive for everyone.☆26Sep 2, 2026Updated 2 months ago
- Automations for GivEnergy inverter, sets daily target SoC, schedules API calls and logs data on PVOutput.org☆12Apr 2, 2026Updated 7 months ago
- A list of OSINT resources tools that may be useful to you when conducting investigations related to Australia☆40Oct 19, 2026Updated 3 weeks ago
- ☆31May 19, 2024Updated 2 years ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Burrow testnet guide☆12Nov 17, 2025Updated 11 months ago
- A Bluetooth OBDII client for Android devices.☆14Feb 10, 2013Updated 13 years ago
- 英字を日本語へ変換するモード式 IME の Neovim プラグイン☆24Updated this week
- ☆26Jul 4, 2026Updated 4 months ago
- SparkPilot puts your NVIDIA DGX Spark to work, free forever.☆16Sep 11, 2026Updated 2 months ago
- Android code to connect the WIFI OBD2 Car Code Scanner. This will measure the car speed and RPM.☆14Aug 25, 2015Updated 11 years ago
- ☆37Updated this week
- Single-pass MiniMax H3 image-to-video for ComfyUI (~166s/7s at 704x384 on one RTX 4060 Ti 16GB).☆19Aug 27, 2026Updated 2 months ago
- The Lounge - Home Assistant Community Apps☆19Updated this week
- 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.
- NVFP4 inference on Blackwell GeForce (RTX 5090/5080/5070 Ti/RTX PRO 6000) — SM120 patches for vLLM + FlashInfer + CUTLASS. 175 tok/s on Q…☆29Apr 27, 2026Updated 6 months ago
- Android向けに実装された、エンジンにmozcを採用している日本語IME☆34Nov 2, 2026Updated 2 weeks ago
- How to create a private Epstein search engine☆16Feb 13, 2026Updated 9 months ago
- An OS-level AI layer for Windows & MacOS powered by pi.☆19Oct 10, 2026Updated last month
- A 2MB sklearn classifier on consumer CPU beats Cohere's $10M+ 218B MoE on HumanEval☆13Oct 18, 2026Updated 3 weeks ago
- Astra orchestrates, Sol implements, DeepSeek V4.1 Flash and Luna support. A quota-conscious Codex skill with verified repair loops.☆11Sep 12, 2026Updated 2 months ago
- A high-performance, zero-trust AI agent in Rust. Single binary featuring CLI assistant, Concourse CI, collaborative Markdown MCP hub with…☆15Nov 4, 2026Updated last week
Are these results useful?