Qwen3.8-27B on a single RTX 4090 (sm_89): Cinference/NInfer port with MTP speculative decoding and K8V4 KV cache
☆14Oct 20, 2026Updated last week
Alternatives and similar repositories for ninfer-4090
Users that are interested in ninfer-4090 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Qwen3.8-27B-GSQ3 on one RTX 4080: 100k context with rk4v4-e8, up to 2720 tok/s prefill and 262 tok/s generation☆30Oct 9, 2026Updated 2 weeks ago
- 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, …☆47Updated this week
- Ternary (2.125 bit/weight) Bonsai 2 27B on the NINFER engine — Ada sm_89, Linux. Derivative work of Neroued/ninfer; see README.☆56Updated this week
- 1.08M cannabis club members, 985K ID scans, no authentication required — CCS Nube / PuffPal disclosure☆19Jun 29, 2026Updated 3 months ago
- Argentina folk dances visualization project☆11Jan 25, 2023Updated 3 years 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.
- create wavefunction file from selected spin, kpoint and band index in VASP wavecar☆14Jan 24, 2022Updated 4 years ago
- Sandbox-Here is a convenience script around bubblewrap to sandbox agents and similar semi-trusted processes☆12Aug 17, 2026Updated 2 months ago
- An implementation of the C standard printf() and related functions for Mathematica☆12Jun 10, 2013Updated 13 years ago
- An experimental webkit-based kernel exploit (Arb. R/W) for the PS5 on <= 4.51FW☆15Apr 20, 2025Updated last year
- Off-Path TCP Hijacking in Wi-Fi Networks via A Packet-Size Side Channel Attack.☆12Sep 12, 2024Updated 2 years ago
- Exercise files for the book titled Functional Programming in PHP☆10Jun 11, 2022Updated 4 years ago
- 15-618 Final Project: Transforming an image to low poly style☆20Dec 16, 2018Updated 7 years ago
- a "easy-to-use" automation script for the PPPwn Exploit by TheFlow.☆12Feb 12, 2025Updated last year
- ☆18Aug 6, 2026Updated 2 months 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.
- react hook sticky☆20Jul 14, 2021Updated 5 years ago
- WebServer+Wifi Repeater+Fake DNS Server to Host PS5 Exploits on ESP8266/ESP32☆15Sep 24, 2024Updated 2 years ago
- Compile JSON to BIND zone files automatically☆14Nov 26, 2025Updated 11 months ago
- Simple portage of Enable/disable Updates from the PS4 collective scene☆17Feb 28, 2023Updated 3 years ago
- ☆12Mar 31, 2025Updated last year
- Event Engine Docs☆13Jan 2, 2022Updated 4 years ago
- BRKN Lifestyle Prompt Composer is a modular ComfyUI prompt randomizer designed to turn reusable packs into fast, varied, and controlled i…☆19Jul 20, 2026Updated 3 months ago
- ValueObjects toolkit, for making your own value objects quickly and easily☆10Nov 10, 2017Updated 8 years ago
- GOAT’d Text Generator 🐐- Turn rough ideas into polished prompts with cloud or local LLMs. Bring images, videos, and audio into the mix, …☆20Updated this week
- 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.
- ☆17Aug 2, 2024Updated 2 years ago
- Let Claude Code / OpenCode delegate coding tasks to parallel Codex subagents via tmux☆16Mar 25, 2026Updated 7 months ago
- Markdown-based persistent memory for OpenCode. Store facts, identity, and daily logs with auto context injection.☆15Mar 4, 2026Updated 7 months ago
- A package for quickly constructing k·p models of magnetic and non-magnetic crystals☆20Aug 25, 2026Updated 2 months ago
- Vibe coded nodes based on smarter people to make their interface the way I want it.☆24Oct 17, 2026Updated last week
- On-device voice isolation, wake words, voice activity and voiceprints. In the browser (WebAssembly) and in Python, with plugins for LiveK…☆26Updated this week
- Designed a smaller architecture implemented from the paper Deep Residual Learning for Image Recognition and achieved 93.65% accuracy.☆10Jan 12, 2023Updated 3 years ago
- Zip Prompt Language - compress heavy system prompts by ≥ 80 % token reduction☆15Jun 6, 2025Updated last year
- Cognitive Loop Runtime for Kubernetes☆24Aug 11, 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.
- DeepSeek-V4 in C99, streamed off NVMe. Runs the 284B Flash checkpoint from 3.2 GB of RAM, 1.81 s/token with a GPU, verified against PyTor…☆23Aug 25, 2026Updated 2 months ago
- AI coding agent for the terminal — PHP 8.4, Symfony TUI, mythology-themed☆20Updated this week
- 514 Krea 2 Turbo prompts with generated examples and ComfyUI wildcards☆31Sep 6, 2026Updated last month
- PS5 Payloads☆18Jan 12, 2025Updated last year
- Descarga la factura de cualquier cliente de Movistar Argentina☆19Nov 16, 2016Updated 9 years ago
- A Golang Text to Speech System☆17Feb 16, 2026Updated 8 months ago
- Getting of model metadata, images/videos and keywords from civitai and visualizing them should be easy.☆18Aug 20, 2026Updated 2 months ago