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.
☆48Oct 26, 2026Updated this week
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:
- Thinking blocks that open during generation: a gate decides when to think, a tree of candidate thoughts is explored, and the best one sta…☆19Oct 11, 2026Updated 2 weeks ago
- An easy to use Unity plugin that allows you to track how much time you have spent working on your unity project.☆17Nov 26, 2025Updated 11 months ago
- Exploring the connection between people and place, production and consumption. Desktop software for managing a homestead or a completed p…☆14Oct 19, 2026Updated last week
- Use CSV files as configuration files in Godot with type definitions.☆15Mar 2, 2024Updated 2 years ago
- Run Qwen Flash Next on a Mac Mini m5 64GB box☆16Updated 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.
- Multi-GPU prefill acceleration for llama.cpp☆15Updated this 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…☆123Updated this week
- Containerized bridges to interconnect services in matrix☆11Oct 20, 2026Updated last week
- A compiler-first PyTorch alternative. MLIR-based Boom IR, Guile scripting, CUDA and CPU. On consumer GPUs it already beats llama.cpp’s LL…☆31Updated this week
- Qwen3.8-Flash-Next (MoE) and Qwen3.8-27B on one or two 16 GB RTX 50-series GPUs: experts offloaded to CPU, two-GPU tensor parallel. 64 GB…☆89Updated this week
- HikVision IP Camera Alarm Server to MQTT☆14Sep 20, 2023Updated 3 years ago
- 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…☆28Oct 7, 2026Updated 3 weeks ago
- A Menu Bar app for macOS and GUI app for WIndows/Linux that allows you to take a screenshot of equations and generate latex code of that …☆11Apr 26, 2023Updated 3 years ago
- Data over sound, measured: 36.6 kbps laptop↔phone acoustic modem — portable C library, adaptive OFDM + graceful degradation to a never-ze…☆15Sep 8, 2026Updated last month
- 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.
- Proxima lets existing GPUs serve 4x more concurrent requests☆26Aug 19, 2026Updated 2 months ago
- ☆29Oct 18, 2026Updated last week
- Token-lean web microfetch for LLM agents: any URL → clean markdown via CLI, MCP server, and Claude Code plugin. Real browser-cookie auth,…☆17Updated this week
- A high-throughput LLM serving engine with non-uniform KV cache compression, built on vLLM☆16Sep 9, 2026Updated last month
- A MCP server for secure Python code execution with artifact capture, virtual environment support, and LM Studio integration☆11Mar 14, 2026Updated 7 months ago
- The code for the Emerald Sequoia apps Emerald Chronometer, Emerald Chronometer for iPad, and Emerald Geneva☆14Aug 22, 2026Updated 2 months ago
- Custom HIP inference engine for AMD MI50/MI60 (gfx906)☆18Oct 4, 2026Updated 3 weeks ago
- A browser-based UI for launching, monitoring, clustering and managing multiple llama.cpp server instances from inside a Docker container.…☆15Updated this week
- View and navigate your selection history!☆33Mar 3, 2026Updated 7 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.
- Docker images and FastAPI service for the withoutBG open weights ONNX model (v3).☆21Oct 17, 2026Updated last week
- The directory page for the people you host services for: no account, multilingual, live status, one tiny container.☆90Oct 22, 2026Updated last week
- DeepSeek-V4.1-Flash 1017 on 1x-2x RX 7900 XTX (gfx1100, ROCm/HIP): max optimizations☆39Updated this week
- All you need to build Factorio native for your iPad☆23Sep 8, 2026Updated last month
- vLLM fork for pascal gpu☆18Mar 13, 2026Updated 7 months ago
- Game inspired by 2048 implemented as KOReader plugin☆24Sep 20, 2026Updated last month
- ☆29Jul 16, 2025Updated last year
- GLM-5.3-Flash EXL3 on one 24 GB RTX 3090 + DDR4: elastic GPU expert cache, zero-copy experts, AVX2 CPU tier, OpenAI API☆345Oct 18, 2026Updated last week
- Generate a citation in the BibTeX format from an ISBN (International Standard Book Number) for a publication.☆14Nov 25, 2021Updated 4 years ago
- 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.
- Dockerized environment to ease odoo development☆17Updated this week
- Phantom-WG is a modular tool for setting up and managing WireGuard VPN infrastructure on your own server. Beyond basic VPN management, it…☆16Oct 16, 2026Updated last week
- Audio Reactive Music GLSL Shader render program.☆11Apr 24, 2026Updated 6 months ago
- Qwen3.8-27B and Qwen3.6-35B-A3B local inference engine for Vulkan and Metal☆76Updated this week
- ☆11Aug 31, 2026Updated last month
- Publish mDNS records based on your Caddyfile☆15Jan 1, 2026Updated 9 months ago
- Local-first, LLM-guided, coverage-driven fuzzer for network protocols and binary formats. Single Rust binary. Zero signup.☆15Jul 14, 2026Updated 3 months ago