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.
☆27Sep 1, 2026Updated 2 months ago
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:
- ☆13Oct 2, 2026Updated last month
- A 21M-parameter LM with a 16.8M-row product-key memory: as good as a 114M dense model and runs with the table on an SSD. Triton kernels f…☆16Oct 23, 2026Updated 2 weeks ago
- USB display bridge for stock DJI Goggles 2 and Goggles Integra; supported on both Windows and macOS☆50Updated this week
- Very op bloxd.io hacks.☆31Feb 23, 2024Updated 2 years ago
- Improving Source Extraction with Diffusion and Consistency Models☆12Jul 18, 2026Updated 3 months ago
- 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.
- Custom llama.cpp fork for running EschaLabs Escha models.☆13Sep 11, 2026Updated last month
- Universal frequency-band splitter for music source separation: one interface for BSRoformer, MelBandRoformer, or any Band Split. RoPE, Po…☆13Nov 1, 2026Updated last week
- 한글 AI 글 윤문·탐지 Claude Code 플러그인 — AI가 쓴 한국어를 사람처럼 윤문하고 AI 작성 여부를 진단☆19Sep 11, 2026Updated last month
- TxtAIEditor - Fast, Free Text & Markdown Editor for Windows. Edit large files, preview Markdown, compare changes, and use AI agent — all …☆16Updated this week
- ☆11Oct 20, 2026Updated 2 weeks ago
- LLM inference in C/C++☆24Oct 21, 2026Updated 2 weeks ago
- Hacker Forum Classification for Threat Intelligence☆12Jan 25, 2022Updated 4 years ago
- Fun terminal roster for Claude / Codex / Cursor / Grok rate limits☆55Oct 5, 2026Updated last month
- A powerful all-in-one Telegram bot for auto request approval, group management, moderation, filters, notes, force subscribe, and automati…☆17Nov 1, 2026Updated last week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- LLM inference in C/C++☆15Aug 27, 2026Updated 2 months ago
- VDWT: low-latency block-free wavelet video codec (beta, binaries)☆29Oct 30, 2026Updated last week
- Sandboxed code execution daemon with enforced memory, CPU, and output limits. JSON API for humans and AI agents.☆13May 21, 2026Updated 5 months ago
- MCP-powered memory, policy, and experience layer for safer AI agents.☆12May 8, 2026Updated 6 months ago
- A convenient way to install and configure the appropriate version of PyTorch on the user's computer, based on the OS and GPU manufacturer…☆15Updated this week
- Remap the Nothing Phone Essential Key to your own actions — no root required.☆28Oct 10, 2026Updated 3 weeks ago
- Singing voice conversion built on LeapSinger's harmonic excitation and rectified flow: content + F0 + loudness -> mel -> NHVSing. Quality…☆24Oct 1, 2026Updated last month
- What actually runs on an RTX 3060 12GB, if you have any card with 12GB vram, this is for you as well. measured, with commands☆162Aug 22, 2026Updated 2 months ago
- Local-first dashboard for inspecting and maintaining a YantrikDB memory store☆13Oct 1, 2026Updated last month
- 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.
- MCP server that connects Claude to local Ollama models, delegating simple tasks to save tokens for complex reasoning☆16Oct 23, 2026Updated 2 weeks ago
- iboot researches☆14Sep 13, 2026Updated last month
- A bare-bones GUI application for the local inference engine, llama.cpp. Built-in TPE optimiser to find the best flags for your system☆18Oct 15, 2026Updated 3 weeks ago
- A diary application that is build with React Native and Expo.☆13Feb 14, 2025Updated last year
- Teaching a humanoid to walk(ish), then displaying in your browser (using tensorflow.js and reinforcement learning)☆10Sep 7, 2020Updated 6 years ago
- An Vulnerability detection and Exploitation tool for CVE-2024-7339☆17Aug 10, 2024Updated 2 years ago
- Rust-host continuation of DwarfStar for explicit, hardware-validated large-model inference on DGX-Spark.☆19Updated this week
- A Python utility for seamless import and export of n8n workflows and credentials. Automates migration between environments, simplifies ba…☆13Apr 8, 2025Updated last year
- 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☆31Nov 2, 2026Updated last week
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Official repository for: Simultaneous Music Separation and Generation Using Multi-Track Latent Diffusion Models☆19Nov 21, 2025Updated 11 months ago
- 中英混著講，落下的是乾淨的繁體中文。macOS 選單列語音輸入，whisper.cpp 全程在本機跑，kubectl、Terraform 這類術語內建修正。☆13Sep 3, 2026Updated 2 months ago
- MCP Server for reasoning☆15Apr 16, 2025Updated last year
- Guided meditation assistant, using scheduled messages with LLaMA☆10Nov 28, 2024Updated last year
- Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.☆15Apr 24, 2025Updated last year
- List of Spine file IDs of BlueArchive Characters like "CH0123" | Blue Archive 学生名称/皮肤名与对应的内部文件名对照表 ("CH0123"/"NP0123"形式的ID) | Filenames …☆20Updated this week
- Mail for AI agents ( and humans). MCP server giving Claude (or any agent) safe, permission-controlled access to email (Microsoft Graph + …☆18Updated this week
Are these results useful?