Run a 177B model (Qwen3.8-Flash-Next) on an 8 GB laptop GPU. Measured: 6.6 GiB VRAM, 47.8 GiB RAM, 34-35 tok/s. The n-gram table stays on disk; the experts run on CPU.
☆24Sep 1, 2026Updated last month
Alternatives and similar repositories for flash-next-8gb
Users that are interested in flash-next-8gb are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆27Sep 11, 2026Updated last month
- Fun terminal roster for Claude / Codex / Cursor / Grok rate limits☆55Oct 5, 2026Updated 2 weeks ago
- Trace AI applications and agents, and monitor token usage, cost, latency, and errors with OpenTelemetry.☆32Updated this week
- LLM inference in C/C++☆143Updated this week
- Install Antigravity 2.0 with one command in Linux (Ubuntu/Debian)☆81Jun 4, 2026Updated 4 months ago
- 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.
- mirror of:☆14Updated this week
- Browser playground and game for llama-server's /v1/decision (Jev-style parallel constrained decisions)☆26Sep 19, 2026Updated last month
- ComfyUI workflows for MiniMax H3 (Ref2VA / FL2VA / VideoRef / Pose Control) at Full HD on 12GB VRAM.☆27Updated this week
- Graphic Devices for R based on NanoVG☆10Jun 15, 2018Updated 8 years ago
- Scripts and related files to install Nik for GIMP on Ubuntu☆18May 26, 2025Updated last year
- SGLang Docker image for AMD Strix Halo (gfx1151 / Radeon 8060S)☆41Sep 17, 2026Updated last month
- Xolotl (formerly Strata-DSV4.1): DeepSeek-V4.1-Flash, all 552B, on one gaming PC (RTX 4090 + 90 GB RAM) at ~27 tok/s, plus GLM-5.3-Flash,…☆164Updated this week
- OpenATP is an open-source Python package providing a common interface for Automated Theorem Proving (ATP)☆30Oct 8, 2026Updated last week
- Open-source 2D architectural editor with a Figma-like interface, a local CLI, and practical workflows for humans and AI agents.☆40Updated this week
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Automatic, model-driven permission review for OpenCode☆32Sep 17, 2026Updated last month
- Singing-voice synthesis & Singing-voice Conversion☆39Sep 21, 2026Updated 3 weeks ago
- An experimental and feature-rich inference engine built on top of llama.cpp☆81Updated this week
- LLM inference in C/C++☆15May 7, 2026Updated 5 months ago
- ☆74Jul 26, 2026Updated 2 months ago
- Merged into the Amecs project: https://github.com/Siphalor/amecs☆15Feb 22, 2026Updated 7 months ago
- Qwen3.8-27B NVFP4 (W4A16 shipped recipe) + MTP on NVIDIA DGX Spark GB10/SM121 — vLLM v0.27.2rc0, FP8 KV, 262K context, full reproducibili…☆27Aug 20, 2026Updated last month
- A diary application that is build with React Native and Expo.☆13Feb 14, 2025Updated last year
- AI powered Remote Control application for Siglent SDS 1000X-E series oscilloscopes☆43Updated 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.
- Reproducible Qwen3.8-27B NVFP4 + DFlash2 recipe and qualification evidence for one NVIDIA DGX Spark☆30Aug 21, 2026Updated last month
- A cool demo web app to show Node.js, Raphaeljs, socket.io, Express.js, Mongoose and MongoDB integration☆13Apr 11, 2015Updated 11 years ago
- Pawchive Downloader is a modern desktop media grabber for Pawchive, Kemono, Coomer, and Cum.st. It features multi-threaded downloads, bui…☆53Updated this week
- Complete guide to running local AI on AMD RX 580 8GB via Vulkan — llama.cpp, Ollama, OpenWebUI, Stable Diffusion. No CUDA. No cloud. Free…☆39Jun 23, 2026Updated 3 months ago
- Automatically updated and decrypted client-side data from Blue Archive game, providing character stats, equipment data, and more for fan …☆24Updated this week
- A collection of Pi coding agent extensions☆26Updated this week
- LLM inference in C/C++☆26Sep 17, 2026Updated last month
- ⚡ Hermes Agent 2026: Next-Gen Multi-AI Desktop Automation Platform☆87Updated this week
- A fast diffusion model engine for image generation and editing.☆35Updated this week
- 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.
- Apple Silicon macOS film development and photo editor with local AI and MCP☆72Oct 4, 2026Updated 2 weeks ago
- The best model under 200B at near 10 token/s exact batch throughput on a single laptop CPU, with an automatic 8 GB RAM path. Native C, no…☆23Sep 9, 2026Updated last month
- RL agent using private and shared world models☆11Jun 12, 2023Updated 3 years ago
- My Configs and Dotfiles 🫥☆18Oct 1, 2026Updated 2 weeks ago
- A powerful all-in-one Telegram bot for auto request approval, group management, moderation, filters, notes, force subscribe, and automati…☆17Oct 1, 2026Updated 2 weeks ago
- Переписывает промпт под правила модели, где вы работаете (Claude Opus 5.5, Fable 5.1, GPT-6 Astra/Sol/Luna, Codex), и подсказывает, на ка…☆128Updated this week
- The free launchpad. Uniswap v4 token launches with zero platform fee and permanently locked liquidity, on Base and Robinhood Chain.☆34Updated this week