project-maya
project-maya is Plus a round of fixes, UI improvements and community PRs.. It is ranked #21 on the AI Radar, in Open & local models, first seen 28 days ago and shared in 31 posts (237.9k views).
What project-maya says about itself
DeepSeek reads prompts (prefill) much faster on AMD Strix / Gorgon Halo and faster on multi-GPU NVIDIA PCs, Qwen-3.8-Flash-Next itself as unsloth's UD-IQ2_XS GGUF, and four community pull requests....
Release v1.1.54 · mw00/project-maya · GitHub Skip to content Navigation Menu Sign in Search / Sign in Sign up Appearance settings You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} Repository navigation v1.1.54 Compare Choose a tag to compare Sorry, something went wrong. Filter Loading Sorry, something went wrong. Uh oh! There was an error while loading. Please reload this page . No results found View all tags mw00 released this 05 Nov…
What people said about project-maya on X
🤯炸了！64GB 内存直接炸开最强开源模型！DeepSeek-V4.1-Flash-1017 本地高性能彻底落地！ Unsloth 正式放出 DeepSeek-V4.1-Flash-1017 全新 GGUF，Dynamic V3.1 量化在多项基准上全面碾压！ 核心亮点 🔹Dynamic V3.1 在 GPQA Diamond、AIME25、LiveCodeBench v6、MMLU-Pro、Aider 等几乎全部基准上排名第一 🔹相比前版性能更强、任务完成更快、输出更短，性价比全面提升 🔹仅需 64GB+ RAM 即可运行（Engram n-gram 支持 SSD offload，大幅降低内存占用） 🔹Unsloth…
— @NFT_Chen, 6 days ago · 941 likes · see the post
Maya v1.1.50 is out 🚀 🧠 GLM-5.3-Flash Maya-XS: a 73 GB GLM for PCs with 64 GB RAM + a 24 GB card, at 128K context. 📦 Models page: download, load, unload and delete models with one click, plus an API for apps and scripts, including swapping models on request. 🔥 Turbo mode: one button for the fastest settings, up…
— @PeasantSmith, 3 days ago · 207 likes · see the post
🤯牛哇！一张英伟达 3090 也能跑748B DeepSeek-V4.1-Flash-1017！解码速度直接翻倍！ @PeasantSmith Project Maya v1.1.28 重磅更新：当RAM装得下experts时，单卡NVIDIA（Linux）解码最高提升约2倍！ 实测（RTX 3090 24GB + Maya-XS）： 12.9 → 27.8 tok/s 优化亮点： 🔹Experts直接从RAM映射拉取到VRAM，零多余拷贝 🔹验证窗口流式处理 + 热点experts留VRAM 🔹完整1M上下文已支持 🔹长代码流式聊天更稳不跳 上手超简单（3步）： 1️⃣git clone…
— @NFT_Chen, 11 days ago · 145 likes · see the post
Alternatives to project-maya
- kimi-k3.1-pro — Releasing the model weights of Kimi K3.1 Pro
- niklaslenz.com — Play the world in your browser. Every number, the exact command and the raw output
- unsloth.ai — Guide to running Mistral Large 4 GGUFs locally with Unsloth and llama.cpp.
- twil-8b — Text Generation model with 9B parameters. Download, explore files and run it on Hugging Face.
- deepseek-harness — I have all three of my AI agent leads for Hermes, Grok Bot, and OpenClaw pouring over the repos for DeepSeeks proposed…
- deepseek-v4.1-flash-1017-gguf — Image-Text-to-Text model with 748B parameters. Download, explore files and run it on Hugging Face.
project-maya in numbers
- Rank on the AI Radar: #21 of 10384
- Shared in 31 posts by 6 accounts: @NFT_Chen, @PeasantSmith, @ItsmeAjayKV, @niklaslenz_ai
- 237.9k views on those posts
- First seen 28 days ago, last shared 18 h ago
- Pricing seen by AGK Intelligence: open source
- Market: Open & local models
FAQ
What is project-maya?
Plus a round of fixes, UI improvements and community PRs. It was first shared on X 28 days ago and is ranked #21 on the AI Radar.
Is project-maya free?
It is open source.
Who shared project-maya?
6 accounts on X, including @NFT_Chen, @PeasantSmith, @ItsmeAjayKV, in 31 posts totalling 237.9k views.
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.7k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 12:45 UTC. Full method.