DeepSeek 4 Flash local inference engine for Metal and CUDA with M5 optimizations.
☆25May 24, 2026Updated 4 months ago
Alternatives and similar repositories for ds4-m5
Users that are interested in ds4-m5 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Run Escha models on Apple Silicon: 2-bit escha runtime for MLX with bit-exact Metal kernels and OpenAI-compatible serving.☆18Sep 16, 2026Updated last month
- ☆21Aug 17, 2026Updated 2 months ago
- Tile primitives for speedy kernels☆21Sep 13, 2026Updated last month
- Production LLM inference on the Apple Neural Engine — a practitioner's guide, complete with converters, Swift runtimes, and validated mod…☆46Jun 7, 2026Updated 4 months ago
- A concept tool for displaying video at any aspect ratio. The video frame adapts to the size and orientation of the device, filling the sc…☆15Jul 21, 2014Updated 12 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.
- Swift implementation of the game Breakout, using SceneKit☆13May 12, 2016Updated 10 years ago
- Split a string into an array based on where an ansi code is present☆13Oct 2, 2017Updated 9 years ago
- Implementation of the HuggingFace Xet Protocol.☆28Aug 13, 2026Updated 2 months ago
- Sushi engine runs very high quality quant model in Apple Silicon, using hybrid affine/exl3 with special expert tuning techniques.☆296Updated this week
- ☆27Jun 7, 2026Updated 4 months ago
- Agent Skill to help convert transformer LLMs to mlx-lm☆51Jun 16, 2026Updated 4 months ago
- 🧩 Plugins and extractors that ArchiveBox + abx-dl use: chrome, ytdlp, wget, singlefile, readability, forum-dl, gallery-dl, papers-dl, an…☆17Updated this week
- Hammerspoon Module used in the Live Enhancement Suite (for macOS)☆17Feb 21, 2025Updated last year
- a remote control for keyboard-driven web presentation systems☆13Apr 10, 2017Updated 9 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.
- H3MLX: MiniMax-H3 Metal 4 / Pure C Video Gen Master Suite, Benchmark Matrix & AI Agent Skill for Apple Silicon☆23Sep 6, 2026Updated last month
- It's an script that helps you to stream video files or video contents to instagram as a live post.☆12Aug 17, 2019Updated 7 years ago
- libxsql core library☆19Oct 10, 2026Updated last week
- Native MLX quants of Qwen3.6-27B-AEON-Ultimate-Uncensored for Apple Silicon (Metal): 8-bit, FP4, and MTP self-speculation. Preserves the …☆42Oct 6, 2026Updated 2 weeks ago
- My collection of dotfiles☆14Apr 22, 2026Updated 6 months ago
- ☆28May 20, 2026Updated 5 months ago
- Output RTSP stream to a virtual webcam device using FFmpeg. A guide.☆12Apr 24, 2023Updated 3 years ago
- ☆14Apr 13, 2026Updated 6 months ago
- Run unmodified native Apple-silicon macOS games on iPad (retag + UIKit shims)☆41Oct 8, 2026Updated 2 weeks ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- "Headroom" context compression layer as wrapped in an Aperture pre-request hook☆22Jul 23, 2026Updated 2 months ago
- Serve DeepSeek-V4-Flash (NVFP4) on 2x RTX PRO 6000 (SM120) with working MTP speculative decoding (+38% single-stream). Root-cause fix: MT…☆18Jun 25, 2026Updated 3 months ago
- Tiny evaluation of leading LLMs on competitive programming problems☆14Apr 10, 2026Updated 6 months ago
- ☆12Jun 14, 2013Updated 13 years ago
- Save content from list of tweet URLs to an HTML file☆13Jul 25, 2015Updated 11 years ago
- DEPRECATED, please use vim-textobj-quote☆16Feb 8, 2014Updated 12 years ago
- AMD SEV-SNP Go unikernel example☆15Oct 9, 2026Updated last week
- Voice to brain interface 🦞🎤🧠 for OpenClaw, Hermes, PI, etc☆25Sep 7, 2026Updated last month
- See where local inference loses speed on Apple Silicon under Linux☆13Updated this week
- 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.
- ☆26Aug 19, 2026Updated 2 months ago
- Official implementation of iSDFT: information-proximal on-policy self-distillation for continual learning in LLMs. Training code, checkpo…☆27Sep 22, 2026Updated last month
- ☆15Apr 25, 2025Updated last year
- Research MIL-to-HWX compiler for the M4 Apple Neural Engine☆16Sep 3, 2026Updated last month
- Windows code for communicating with a VC707 evaluation board running a MIAOW compute unit.☆11Oct 20, 2015Updated 11 years ago
- MLX (Apple Silicon) port of MiniMax-H3 — 33B joint video+audio diffusion. Validated against the diffusers reference; AdaLN precompute dro…☆28Oct 8, 2026Updated 2 weeks ago
- Concurrency Patch to enable on DSpark - DeepSeek V4 Flash/Pro C=16 can be modified for more☆12Jun 29, 2026Updated 3 months ago