Almond: a multi-model MoE engine for AMD RX 7900 XTX (ROCm/HIP) - DeepSeek-V4.1-Flash, GLM-5.3-Flash, Qwen3.8-Flash-Next
☆53Nov 6, 2026Updated this week
Alternatives and similar repositories for Almond
Users that are interested in Almond are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A set of performant RDNA/HIP patches against llama.cpp focusing on high speed inferencing with numerics assurance☆236Updated this week
- Xolotl: run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM): ~33 tok/s on agent tasks, ~4…☆479Updated this week
- Working on the fastest vllm path for AMD Radeon AI PRO R9700☆107Updated this week
- Multi-GPU (tensor-parallel) CUDA megakernel for Qwen3.8-27B GGUF (Q4_K_M, Q5_K_M, Q6_K, Q8_0) with on-device MTP speculative decoding. Fo…☆16Oct 23, 2026Updated 2 weeks ago
- PSP static recompiler: Rust analyze/decode/emit pipeline producing C++17, with an SDL2 + OpenGL runtime☆16Oct 2, 2026Updated last month
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- llama.cpp with native AMD RDNA4 (gfx1201) ROCm 7.11 support - 98.97 tok/s AI inference, competitive with RTX 4070 Ti, 32GB VRAM☆12Jan 3, 2026Updated 10 months ago
- Run GLM-5.3-Flash (321B), DeepSeek-V4.1-Flash (748B) and MiniMax-M3.1-Flash (428B) on your own GPUs - one engine, one dashboard, OpenAI- …☆2,632Updated this week
- A minimal, hackable implementation of Claude’s code☆12Dec 7, 2025Updated 11 months ago
- LLM inference in C/C++☆65May 7, 2026Updated 6 months ago
- ☆12Jan 13, 2026Updated 9 months ago
- A toy PyTorch implementation of FLUX diffusion transformers☆15Aug 3, 2026Updated 3 months ago
- An open benchmark arena for coding agent harnesses, built for the Pi community☆12Oct 21, 2026Updated 2 weeks ago
- Typed JSON inference with DiffusionGemma, with Every and Jev benchmark results☆43Sep 16, 2026Updated last month
- MCP server that shrinks logs, JSON, docs and web pages before your AI reads them. Offline, deterministic, ~3ms, no API key. 66% fewer tok…☆25Oct 21, 2026Updated 2 weeks 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.
- Propoplex is an AI-powered platform that helps freelancers write compelling and optimized proposals for popular freelancing sites, and ma…☆14Jun 13, 2023Updated 3 years ago
- Real-time conversational AI with voice cloning and emotion detection. Analyzes conversation context to deliver dramatically expressive re…☆12Jun 8, 2025Updated last year
- Sandbox-Here is a convenience script around bubblewrap to sandbox agents and similar semi-trusted processes☆12Updated this week
- Union mount in Haskell, with fsnotify☆12May 11, 2026Updated 5 months ago
- A zero-embedding approach to video intelligence, using Jev: contact sheets + typed decisions, as MCP tools and a skill for any coding age…☆54Updated this week
- Various Scripts w/Discord Embeds for my Homelab☆13Dec 16, 2023Updated 2 years ago
- Deterministic PyGhidra extraction, triage, and local LLM compiler-backend pipeline for C reimplementation.☆11Oct 18, 2026Updated 3 weeks ago
- A Claude skill that audits your codebase for GDPR and EU AI Act compliance and returns a ranked list of fixes. Inspired by Flagged.☆11Aug 27, 2026Updated 2 months ago
- A CUDA-accelerated GGUF quantization tool for NVFP4/MXFP6/Q_K, utilizing layer by layer quantization and selection techniques to reduce e…☆49Aug 15, 2026Updated 2 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Glyph3D but for the webbies☆13Updated this week
- ☆18Updated this week
- APISignature is a plugin for x64dbg that help the malware analysts & reverse engineers during analysis by adding a reference for more tha…☆38Aug 15, 2026Updated 2 months ago
- ValueObjects toolkit, for making your own value objects quickly and easily☆10Nov 10, 2017Updated 8 years ago
- Actual real-world ransomware coded in WinAPI C++ with the help of the Cryptography API made to encrypt a whole Windows installation☆12Sep 5, 2023Updated 3 years ago
- 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…☆137Updated this 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
- 🟢 A modern desktop workspace for Claude Code. Open source.☆11Jul 31, 2026Updated 3 months ago
- ☆114Updated this week
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- An AI-based story writer and Python library which uses OpenAI's chatGPT and Dall-E to generate PDFs with a story and a picture from a pro…☆24Feb 23, 2024Updated 2 years ago
- OpenAI-compatible proxy that makes local LLMs serving easy and reliable. Sits between your client and any OpenAI-compatible backend, add…☆14Oct 19, 2026Updated 2 weeks ago
- AI-powered stem separation VST plugin using Demucs/Spleeter☆14Dec 12, 2025Updated 10 months ago
- Skulk is an interconnect fabric for multi-node AI compute; it features intelligent model storage, adjustable sharding, speculative decodi…☆13Updated this week
- A Nix flake ❄️ for configuring my boxen using NixOS, Home Manager, Disko, Stylix, and more. Now in dendritic-ish style!☆12Updated this week
- ☆17Updated this week
- Imaging library targeting many versions and implementations of Python language on Windows, Linux and MacOS.☆11Jan 22, 2014Updated 12 years ago