Fastest validated sglang recipe for Qwen3.8-27B (AWQ-INT4 + DSpark) on RTX 3090s — 1×/2×/4× GPU presets, image+video, full benchmarks
☆64Oct 17, 2026Updated 3 weeks ago
Alternatives and similar repositories for qwen-serve
Users that are interested in qwen-serve are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Production Docker deployment for Qwen3.8-27B AutoRound W4A16 (Vishva007) on 2x RTX 3090 (NVLink or PCIe). OpenAI-compatible vLLM with MTP…☆19Aug 20, 2026Updated 2 months ago
- OpenAI-compatible inference server for 4-bit Qwen3.8-27B on one RTX 3090, 262K context☆34Oct 29, 2026Updated last week
- Qwen3.8-27B on One RTX 3090: 14 hours of measurements. Vision crash fix, VRAM math, MTP tuning, quantisation comparison, and 9 pieces of …☆13Aug 17, 2026Updated 2 months ago
- 两张 V100 跑 Qwen3.8-27B 到 100 tok/s（186K 上下文）：重写 sm70 注意力内核 + 多卡张量并行。Fork of geoffwatts/ninfer-v100.☆19Sep 28, 2026Updated last month
- Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when …☆2,652Updated this week
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- go-dydx is a go client library for dYdX exchange API.☆16Mar 26, 2024Updated 2 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
- llama-server start/stop scripts for Qwen3.6-35B-A3B UD-Q8_K_XL GGUF on DGX Spark☆26Jul 6, 2026Updated 4 months ago
- Qwen3.8 Flash Next AWQ INT4 4x3090 v1: 262K, Vision, FP8 QSA KV and CUDA Graphs on 4x RTX 3090☆16Aug 30, 2026Updated 2 months ago
- Local AI registry: one validated recipe per machine, with the evidence attached☆293Updated this week
- Bend2 - WIP☆16Jun 17, 2025Updated last year
- Benchmarking LLMs in ambiguous non-trivial coding tasks☆15Oct 22, 2026Updated 2 weeks ago
- Optimized VLLM for Ampere☆25Oct 18, 2026Updated 3 weeks ago
- llama.cpp fork for significantly improved performance on Ampere generation Nvidia cards (especially RTX 3090 / 3090 Ti): example: 110+ to…☆310Updated 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.
- DeepSeek-V4.1-Flash-1017 (552B MoE + 196B Engram) on 2x RTX 3090 + 128 GB RAM. Rust + CUDA, T16 quantization. 40+ tok/s measured with exp…☆98Nov 4, 2026Updated last week
- Local LLM speed measurements from a 4x RTX 3090 rig, with exact launch commands and per-run provenance.☆18Aug 15, 2026Updated 2 months ago
- Experimental llama.cpp fork for inference research and development☆907Updated this week
- ☆36Sep 22, 2026Updated last month
- ☆22Sep 1, 2026Updated 2 months ago
- Free CC0 daily dumps of the public record of US markets: congress trades, insider filings, 13F holdings, contracts and grants, lobbying, …☆26Sep 24, 2026Updated last month
- Lightweight Rust reimplementation of OpenClaw — self-hosted AI assistant, <10MB idle RAM, WASM sandboxed tools☆14Mar 1, 2026Updated 8 months ago
- Text along any curve in Flutter, cursive joins kept closed: Arabic, Persian, Urdu, Devanagari, Bengali and script hands.☆27Oct 29, 2026Updated last week
- Browser-based Level Devil fan recreation — rage platformer with perfectly planned traps. Pure HTML/CSS/JS.☆30Jun 13, 2026Updated 4 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.
- Open-source tool for testing AI voice agents☆18Sep 23, 2026Updated last month
- Point any coding harness (Claude Code, Codex, OpenCode, Pi, OMP, Crush, Copilot, Grok…) at any OpenAI/Anthropic/Responses-compatible infe…☆92Sep 27, 2026Updated last month
- EXL3 (exllamav3 trellis) inference on Intel Arc Battlemage: bit-exact ESIMD kernels as a vLLM XPU plugin☆38Sep 26, 2026Updated last month
- Venster is a highly native Windows GUI toolkit for Python based on the ctypes ffi library.☆12Mar 9, 2010Updated 16 years ago
- Halowin Bubo: gufo for native Windows with AMD HIP, tuned for Strix Halo laptops☆24Nov 4, 2026Updated last week
- My emacs developer customization☆11Jan 29, 2012Updated 14 years ago
- Open-source execution relay for trading alerts. TradingView webhooks or AI agents in, broker orders out. Safety rails on by default, a fu…☆33Sep 24, 2026Updated last month
- Process all your context faster with LLMs that can skim and selectively read what matters☆115Updated this week
- A llama.cpp fork with TurboQuant/TCQ KV cache, fused Qwen MTP speculative decoding, and multi-GPU long-context serving fixes.☆25Aug 19, 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.
- https://www.pkief.com/blog/how-to-debug-typescript-with-vs-code☆10Jun 13, 2020Updated 6 years ago
- Profile repo — categorized index of NVFP4 model releases, DGX Spark inference stacks, Apple Silicon MLX builds, the voice-AI stack, and t…☆41Oct 6, 2026Updated last month
- CloudFlare worker as a proxy to Google Generative Language API.☆19Oct 16, 2024Updated 2 years ago
- Zero-dep streaming markdown for the browser — Rust→WASM, 100% CommonMark 0.31 + GFM. Built to not melt the main thread on concurrent LLM …☆10Sep 15, 2026Updated last month
- Standalone Robinhood Chain LP explorer, accounting and research terminal☆65Nov 4, 2026Updated last week
- Interactive canvas for taking an LLM apart tensor by tensor: measured INT8/INT4/FP8 error, distributions, spectra and outlier channels fo…☆74Sep 2, 2026Updated 2 months ago
- ☆16Jul 18, 2023Updated 3 years ago
Are these results useful?