27B at 256k context on one RTX 5090 — FP6 + 4-bit KV + MTP spec-decode, hand-written SM120 tensor-core kernels, OpenAI API.
☆18Aug 18, 2026Updated 2 months ago
Alternatives and similar repositories for qwentin
Users that are interested in qwentin are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Fast LLM server for NVIDIA Blackwell: GeForce RTX 50 and RTX PRO. Qwen3.8-27B on one RTX 5090: 91-94 tok/s, 1.3x vLLM and 1.4x llama.cpp.…☆47Updated this week
- The fastest inference engine for Qwen3.8-27B on the NVIDIA RTX 5090: up to 500 tokens/s for one agent and up to 2,000 tokens/s for many, …☆39Updated this week
- Verified multi-source distribution for local LLM weights☆16Updated this week
- Row-wise block scaling for fp8 quantization matrix multiplication. Solution to GPU mode AMD challenge.☆19Feb 9, 2026Updated 8 months ago
- Unofficial mobile PWA for Hermes Agent — installs as a plugin in your Hermes Dashboard (web UI) and adds a Mobile tab. Chat, approve acti…☆32Sep 20, 2026Updated last month
- 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.
- Strata for a PC with two NVIDIA GPUs and 32 GB of RAM: the low-RAM mode on a layer split, both cards working at the same time. 143 tok/s …☆35Oct 6, 2026Updated 2 weeks ago
- DATV on 13 cm with ESP32: stand-alone ESP32-C3 DVB-S2 beacon and ATV RX, an ESP32-S3 + Android receiver (beta)☆20Updated this week
- Sigil: an in-house RV64GCV RISC-V core and SoC with hardware hashing (SHA-2/SHA-3/Keccak) and signature verification (Ed25519, secp256k1)☆25Updated this week
- macOS menu bar app that keeps your Mac awake, even with the lid closed☆26Oct 14, 2026Updated last week
- iOS swift 扫描线种子填充算法 涂鸦☆17Jun 1, 2021Updated 5 years ago
- Enumerate user accounts and registered authentication methods via the Microsoft Self-Service Password Reset (SSPR) portal☆56Sep 15, 2026Updated last month
- ☆26Updated this week
- Specialized fork for (relatively) fast single-GPU inference (in CUDA) using large MoE models that don't fit fully into VRAM☆17May 6, 2026Updated 5 months ago
- IMMA-based **FP8-as-storage** GEMM experiments for Ampere (sm_86 / RTX 3090 Ti).☆28Jan 30, 2026Updated 8 months ago
- 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.
- A minimal external-display controller for Apple Vision Pro on custom firmware.☆21Oct 8, 2026Updated 2 weeks ago
- reinvented groq LPU, built to run inference on MicroGPT☆50Aug 24, 2026Updated last month
- Deployment kit: Qwen3.8-27B EXL3 3.5bpw target + DFlash2 EXL3 5.0bpw speculative draft — launcher, config, model cards☆232Sep 1, 2026Updated last month
- Grok-powered agent swarms skill for Hermes Agent using TMUX and native kanban☆14May 15, 2026Updated 5 months ago
- ☆33Jun 28, 2026Updated 3 months ago
- Androidホームアプリ FiiLDA Launcher の配布ページ☆26Updated this week
- ☆57Sep 27, 2026Updated 3 weeks ago
- Tensor parallelism is all you need. Run LLMs on an AI cluster at home using any device. Distribute the workload, divide RAM usage, and in…☆18Nov 11, 2024Updated last year
- LLM inference in C/C++☆34Aug 1, 2026Updated 2 months ago
- 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.
- Hot-switch a rooted Samsung phone between One UI and a LineageOS 23.2 GSI via a userspace pivot_root container☆61Updated this week
- SRAM-based arbitrary IQ transmission for ESP32-S3 and ESP32-S31, with selectable sample rates, QPSK/16QAM OFDM waveforms, and E310 spectr…☆24Oct 15, 2026Updated last week
- PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation☆33Nov 16, 2024Updated last year
- Handle Android "draw over other apps" permissions and queries in a version-agnostic way☆22Jun 17, 2019Updated 7 years ago
- This script is designed to streamline the process of scanning a list of IP addresses from AbuseIPDB and extracting valuable information. …☆10Sep 10, 2023Updated 3 years ago
- Re-implemented UNIX-like kernel "zedBSD" and touch-oriented Wayland desktop "Keiland"☆41Updated this week
- Free and Open Source software download manager☆15Mar 30, 2023Updated 3 years ago
- DeepSeek-V4.1-Flash on two NVIDIA DGX Sparks: EXL3 weights from the official checkpoint, upstream vLLM with our patches and decode kernel…☆42Updated this week
- App Notification Library for Jailbroken Devices☆12Jun 2, 2024Updated 2 years ago
- 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.
- Multi-dataset evaluation of Anthropic's J-Space on Qwen3-4B. Demonstrates that internal 'workspace noise' can reliably route high-confide…☆13Jul 13, 2026Updated 3 months ago
- Yet another frontend for LLM, written using .NET and WinUI 3☆11Sep 14, 2025Updated last year
- KMD is a collection of conversational exchanges between patients and doctors on various medical topics. It aims to capture the intricaci…☆23Nov 15, 2023Updated 2 years ago
- LLM inference in C/C++☆56Aug 8, 2026Updated 2 months ago
- Network scanning tool designed to detect and report changes in open ports and services over time☆13Oct 16, 2025Updated last year
- Proof of concept: Exploiting temporal coherence in LLM inference-- delta encoding for KV cache compression and weight-skip prediction. …☆51Apr 10, 2026Updated 6 months ago
- Agent-first CLI loop for Resonite development through ResoniteLink and Flux-SDK.☆46Updated this week