Ternary Bonsai 2 27B MLX inference speedup benchmark engine
☆35Nov 4, 2026Updated this week
Alternatives and similar repositories for mlxfast-bonsai2-27b-engine
Users that are interested in mlxfast-bonsai2-27b-engine are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Lightweight ternary QAT for ternary Bonsai models by Prism-ML☆16Sep 18, 2026Updated last month
- Code, prompts, protocols, and reproducibility materials for Substrates.☆17Sep 6, 2026Updated 2 months ago
- Bonsai 2 27B: 262k context (trained max) on 12 GB, 54 to 97 tok/s decode, 2x prefill, q8_0 KV recipe, grammar tool calls 9/9. Same ternar…☆100Updated this week
- Node.js library for the OpenAI API☆16Jun 23, 2023Updated 3 years ago
- Trading instruments for large timeseries☆11Dec 12, 2022Updated 3 years 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.
- Open Design — Local-first, agent-native design-as-code with the open-source Claude Design alternative. By Mehran Mozaffari.☆10Sep 5, 2026Updated 2 months ago
- Enhance awesome Tweetie for Mac☆11May 11, 2009Updated 17 years ago
- ☆12Jun 7, 2025Updated last year
- LLM-first Three.js WebGPU scene and animation authoring with a persistent native viewport and typed MCP editing☆25Updated this week
- Lightweight, fast and simple cross-platform processing tool for importing and exporting spreadsheet documents.☆14Sep 21, 2026Updated last month
- Ultra-Sparse Adaptation of 1-Bit LLMs via XOR Patches☆90Aug 6, 2026Updated 3 months ago
- Official Implementation for Pre-print "T2MLR: Transformer with Temporal Middle-Layer Recurrence"☆12Sep 8, 2026Updated 2 months ago
- Routing-aware expert paging for memory-constrained MoE serving — a vLLM plug-in with byte-identical outputs and joint expert/KV memory al…☆15Sep 15, 2026Updated last month
- RubyIZUMI☆12May 20, 2008Updated 18 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.
- Speeds up TTFT☆24Sep 25, 2026Updated last month
- A 21M-parameter LM with a 16.8M-row product-key memory: as good as a 114M dense model and runs with the table on an SSD. Triton kernels f…☆16Oct 23, 2026Updated 2 weeks ago
- Multitouch counter for iPhone / iPod touch / iPad☆10Apr 6, 2010Updated 16 years ago
- A Jekyll plugin for responsive images using ImageMagick. Works with Jekyll 4.☆14Mar 3, 2024Updated 2 years ago
- ☆11Updated this week
- Test Wakanda server-side javascript API with this application demo☆15Mar 21, 2014Updated 12 years ago
- ☆10Sep 7, 2022Updated 4 years ago
- Preference-supervised naturalness scorer for modern neural TTS . best way to measure naturalness☆21May 29, 2026Updated 5 months ago
- A simple CLI based tool to perform tasks with AI☆14Jun 21, 2026Updated 4 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆12Jun 1, 2023Updated 3 years ago
- Automatically exported from code.google.com/p/smhasher☆16Mar 10, 2021Updated 5 years ago
- Interactive brokers integration for live trading using Rob Carver's pysystem trade backtester.☆10May 15, 2018Updated 8 years ago
- Enklayve is a secure, privacy-first desktop app that lets you ask your own documents anything, answered by AI models running entirely on …☆12Oct 26, 2026Updated last week
- One serving daemon for local LLM inference — across runtimes and machines.☆22Updated this week
- Free Admin Templates Collection☆16Oct 11, 2012Updated 14 years ago
- Communicating with NATS using the HTTP protocol.☆19Jun 22, 2024Updated 2 years ago
- Binary arithmetic reimagined in Swift☆11Apr 5, 2025Updated last year
- Custom Widgets to integrate in Wakanda Framework and Wakanda GUI Designer☆14Jun 4, 2015Updated 11 years 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.
- Compare performance between a Rust FFI and a Rust-compiled-to-WASM for the Collatz conjecture.☆10Apr 21, 2024Updated 2 years ago
- A simple template jit compiler for a subset of Python☆14May 3, 2019Updated 7 years ago
- Using GRPO and a modified compositional reward function to train an opensource model on the 1890 Dakota Dictionary☆14Updated this week
- The MaleCNS fruit-fly connectome, run unchanged, plays Doom E1M1 through a hand-built eye and a trained readout☆23Sep 26, 2026Updated last month
- Route application audio and manage PipeWire device profiles and Bluetooth codecs☆18Oct 24, 2026Updated 2 weeks ago
- One-step Turkish text-to-speech trained with a drifting objective (Kyutai learned-temperature recipe)☆27Oct 16, 2026Updated 3 weeks ago
- Improving Text-to-Image Models with Large Language Models☆23Oct 18, 2022Updated 4 years ago