Validated recipe for serving Qwen3.6-27B on a single RTX 5090 — full OpenAI API, vision, tool calling, MTP spec-decode
☆74Apr 29, 2026Updated 6 months ago
Alternatives and similar repositories for qwen36-27b-single-5090
Users that are interested in qwen36-27b-single-5090 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- SNDR Core Engine (Genesis) — vLLM runtime patch-overlay for Qwen3.6 + Gemma4 on consumer NVIDIA (Ampere sm_86, 2× A5000/3090). Qwen3.6-35…☆133Sep 30, 2026Updated last month
- Quasar is an inference engine for Qwen3.6-27B-MTP / Qwen3.8-27B on consumer NVIDIA cards as well as Apple Silicon, in the spirit of antir…☆53Updated this week
- One-click Qwen3.6-27B inference on Windows. 158 tok/s on RTX 5090, 72 tok/s on RTX 3090. Native, no WSL, no Docker, no telemetry.☆230May 14, 2026Updated 5 months ago
- ☆119Apr 28, 2026Updated 6 months ago
- Optimized cross-platform expansion of autoresearch.☆18Mar 23, 2026Updated 7 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- An inference engine for one NVIDIA RTX card, built for a coding agent and its subagents, and a companion that listens, reads and draws: Q…☆63Updated this week
- Docker deployment of Qwen3.8-27B (NVFP4) on a single RTX 5090: Full native 256K-token context (FP8 KV) + MTP working at 120-170 tokens/s,…☆13Sep 5, 2026Updated 2 months ago
- Rust reimplementation of Laya, a sub-35ms non-autoregressive typed-decision engine (ModernBERT encoder + RLCD-trained decision head), bui…☆14Oct 18, 2026Updated 3 weeks ago
- ComfyUI nodes and H3 workflows for single and dual character replacement, SAM mask repair, and full-clip timing☆14Sep 14, 2026Updated last month
- An electron Wrapper for Open-Interpreter for the lablab.ai hackathon☆12Oct 14, 2023Updated 3 years ago
- Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, sglang, llama.cpp and other custom engines) and m…☆2,488Updated this week
- NVFP4 inference on Blackwell GeForce (RTX 5090/5080/5070 Ti/RTX PRO 6000) — SM120 patches for vLLM + FlashInfer + CUTLASS. 175 tok/s on Q…☆28Apr 27, 2026Updated 6 months ago
- Minimax H3 Specific Lora Stack Loader with some additional features.☆20Oct 11, 2026Updated last month
- ☆31Aug 28, 2026Updated 2 months 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.
- Keep Pi conversation separate from tool output and agent activity.☆16Updated this week
- A modern Q&A platform built with Next.js, featuring role-based access control (RBAC) using Clerk. This full-stack app demonstrates enterp…☆11Mar 13, 2025Updated last year
- LLM inference in C/C++☆12Oct 18, 2026Updated 3 weeks ago
- Lean 4 formalization of Knuth's 'Claude's Cycles' paper☆17Aug 26, 2026Updated 2 months ago
- A desktop application for macOS and Windows that allows users to select an area of their screen and receive an AI-generated description o…☆17Oct 20, 2025Updated last year
- Repairs predictable tool-call mistakes that often derail open weight models. Supports integration with other extensions' custom tools.☆13Jul 21, 2026Updated 3 months ago
- open-source mac menu bar app that allows you to clip python scripts☆15Aug 9, 2026Updated 3 months ago
- Build different debian suites for the radxa rock 4 se☆12Mar 11, 2024Updated 2 years ago
- a library of 100+ Sora 2 prompts☆16Oct 11, 2025Updated last year
- 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.
- ☆12Oct 9, 2023Updated 3 years ago
- Clean AI-generation artifacts from Suno tracks, then master for release. Free, offline, runs entirely on your machine.☆22Sep 25, 2026Updated last month
- Aurelia bind table integration for RethinkDB via Socket.io☆16Apr 1, 2017Updated 9 years ago
- Sample app demonstrating Aurelia Material Design Lite binding☆15Jul 20, 2015Updated 11 years ago
- Serving large LLMs on a single DGX Spark (121 GiB): Qwen3.8-Flash-Next on TensorFold/SparkFold EXL3 and vLLM NVFP4, Nemotron 3.5 Super VL…☆27Oct 21, 2026Updated 3 weeks ago
- Qwen3.6-27B on dual RTX 3090 — TP=2 recipe, vLLM nightly, MTP + fp8 KV, validated for concurrent serving☆57Apr 28, 2026Updated 6 months ago
- LLM quantization optimizer☆23Aug 20, 2026Updated 2 months ago
- ☆11Oct 22, 2026Updated 2 weeks ago
- ☆25Nov 1, 2026Updated last 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.
- Personal pi agent setup☆16Mar 16, 2026Updated 7 months ago
- Async flow control for directed-acyclic-graph iteration.☆16Nov 12, 2012Updated 13 years ago
- Supplemental utilities to help with processing data replicated into Hadoop☆14Apr 16, 2018Updated 8 years ago
- The category map for agent credential management. Products, integrations, recipes, patterns, threat models. Curated by Authsome.☆12Jun 2, 2026Updated 5 months ago
- A set of Comfyui nodes☆21Nov 1, 2026Updated last week
- Google Chrome extension that allows mass blocking of authors for the social media platform Ekşi Sözlük.☆17Sep 6, 2026Updated 2 months ago
- GLM-5.3-Flash on two NVIDIA GB10 nodes: versioned ARM64 images, one terminal launcher, native TP2 and image input☆15Oct 18, 2026Updated 3 weeks ago
Are these results useful?