Qwen3.8-Flash-Next at full 262k context on 8 GB RAM and 16 GB VRAM—20 tok/s generation and 1,600 tok/s prefill.
☆67Oct 26, 2026Updated 3 weeks ago
Alternatives and similar repositories for lean-qwenflash
Users that are interested in lean-qwenflash are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- GLM-5.3-Flash EXL3 on one 24 GB RTX 3090 + DDR4: elastic GPU expert cache, zero-copy experts, AVX2 CPU tier, OpenAI API☆352Oct 18, 2026Updated last month
- Lightweight ternary QAT for ternary Bonsai models by Prism-ML☆16Sep 18, 2026Updated 2 months ago
- Thinking blocks that open during generation: a gate decides when to think, a tree of candidate thoughts is explored, and the best one sta…☆18Oct 11, 2026Updated last month
- Qwen3.8-Flash-Next at 262K context on an RTX 5090 + RTX 4070 Ti SUPER with 32 GB RAM: Strata patches (prefill on the big card, conversati…☆38Nov 11, 2026Updated last week
- An offline coding agent for local models. One command sets up the best model your GPU can run, and on 24 GB+ RTX 30/40/50-series cards Qw…☆147Updated 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.
- Docker images and FastAPI service for the withoutBG open weights ONNX model (v3).☆26Updated this week
- Claude Code's first turn opens the right file instead of grepping — a local static-analysis repo graph injected before turn 1 (no embeddi…☆10May 28, 2026Updated 5 months ago
- ☆11May 7, 2026Updated 6 months ago
- ☆27Sep 11, 2026Updated 2 months ago
- Containerized bridges to interconnect services in matrix☆11Oct 20, 2026Updated 3 weeks ago
- SSH MCP Server - Connect to remote servers via SSH and execute commands through Model Context Protocol☆13Jun 11, 2025Updated last year
- Be the CEO of the modern world☆16Updated this week
- ☆25Feb 10, 2026Updated 9 months ago
- ☆18Oct 11, 2026Updated last month
- 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.
- Branch-Thinking MCP Tool A TypeScript-powered MCP server for managing parallel branches of thought, semantic cross-references, and persis…☆15Apr 25, 2025Updated last year
- An Infinitely Expandable Keyboard built during Hackclub Highway!☆18Aug 9, 2025Updated last year
- Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith …☆1,163Updated this week
- Berth is a lightweight GPU resource manager written in Go. It controls which applications get access to your GPU, when they get it, and h…☆299Updated this week
- ∞ TAPEDECK — infinite personal AI radio. Turn folders of songs into endless local stations: ComfyUI + MiniMax Music 3, taste-modeled from…☆47Updated this week
- Run Qwen Flash Next on a Mac Mini m5 64GB box☆20Updated this week
- Codex-style multi-agent orchestration for pi☆21Mar 26, 2026Updated 7 months ago
- 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
- copyparty with patent-restricted features added back in☆14Oct 15, 2026Updated last month
- 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.
- Progressive learning guide for Pi coding agent extensions☆23Nov 6, 2026Updated last week
- Copilot Chat extension for VS Code☆16Jul 17, 2025Updated last year
- An open-source Parsec client for Android. This repo implements mouse & keyboard & touch screen support.☆16May 31, 2026Updated 5 months ago
- Fast LLM inference in pure C++☆19Jul 18, 2026Updated 4 months ago
- python command-line Text-to-Speech (TTS) tool esp. for German, leveraging numerous endpoints like orpheus, piper, outetts, kokoro, csm, e…☆16Oct 1, 2026Updated last month
- SonicBoom is a compiler-first PyTorch alternative for language, vision, audio, and training. It builds on proven kernels and pushes perfo…☆34Updated this week
- System One coding agents: code-level answers in about 10secs for under 2 cents. On the 74-point xz benchmark the ultra-fast local profile…☆34Updated this week
- Automates the creation of full-text (sound and text) ebooks in epub/epub3/daisy format, the webserver/client creates smil files to sync a…☆11Nov 12, 2021Updated 5 years ago
- 🤖 302 AI Academic Thesis Search! 🚀✨☆12Aug 26, 2025Updated last year
- 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.
- Qwen3.8-27B and Qwen3.6-35B-A3B local inference engine for Vulkan and Metal☆84Updated this week
- A browser-based UI for launching, monitoring, clustering and managing multiple llama.cpp server instances from inside a Docker container.…☆15Updated this week
- Coding agent where a 0.8B decision model works alongside Qwen 3.8-27B: Jeff takes the routine steps itself and decides when Qwen should t…☆35Oct 7, 2026Updated last month
- Token-lean web microfetch for LLM agents: any URL → clean markdown via CLI, MCP server, and Claude Code plugin. Real browser-cookie auth,…☆18Updated this week
- JSON containing the list of irregular verbs per language (work in progress)☆10Sep 22, 2020Updated 6 years ago
- Generate a citation in the BibTeX format from an ISBN (International Standard Book Number) for a publication.☆14Nov 25, 2021Updated 4 years ago
- A collection of scripts for automating animation in Blender☆11Aug 2, 2020Updated 6 years ago
Are these results useful?