Up to 4× faster LLM decoding on Apple Silicon, lossless. Native MLX port of DeepSeek's DSpark & z-lab's DFlash speculative decoding — Gemma-4, Qwen3.8, Muse-Glimmer, Nemotron, LFM2.5, Ornith-1.0, ternary Bonsai-27B.
☆737Nov 8, 2026Updated this week
Alternatives and similar repositories for mlx-dspark
Users that are interested in mlx-dspark are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B…☆2,697Updated this week
- Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swift frontend macOS app with c…☆2,439Updated this week
- A local inference engine for Apple silicon, built around the model.☆2,218Updated this week
- LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar☆23,564Updated this week
- vMLX - Use MLX models easily - JANGQ (GGUF for MLX) - Not dependant on mlx_vlm☆916Updated this week
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused o…☆4,134Updated this week
- APx, or Agentic Power, is a framework for measuring the useful work produced by agent systems—not just how long agents run or how many ta…☆10Oct 10, 2026Updated last month
- LLM Inference Engine for Metal, CUDA and Vulkan.☆1,935Updated this week
- Qwen 3.8 27B at 48-65 tok/s on a Mac Studio M4 Max — measured oMLX native-MTP recipe, same-day A/B vs mlx-vlm+MTP sidecar, raw benchmark …☆71Aug 21, 2026Updated 2 months ago
- A MLX port of FLUX based on the Huggingface Diffusers implementation.☆20Sep 20, 2026Updated last month
- Lossless DFlash speculative decoding for MLX on Apple Silicon☆793Aug 20, 2026Updated 2 months ago
- DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm☆24,336Updated this week
- Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unslot…☆1,470Jun 23, 2026Updated 4 months ago
- DFlash block-diffusion speculative decoding running on Apple Silicon via MLX, with an ANE execution path that explores heterogeneous acce…☆62Apr 18, 2026Updated 6 months 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.
- DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm☆17Oct 22, 2026Updated 3 weeks ago
- MiniMax H3 inference engine for Mac computers☆3,057Aug 11, 2026Updated 3 months ago
- MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.☆5,840Updated this week
- Blazing fast Apple Silicon inference engine optimized for Qwen & Nemotron. OpenAI + Anthropic API compatible. Built by folks from nace.ai☆759Updated this week
- Minimal Claude Code alternative powered by MLX☆47Jan 11, 2026Updated 10 months ago
- Run LLMs with MLX☆7,639Updated this week
- MiniMax H3 (video + audio) on TensorFold 0.6.5 with an H3 family, Mac Studio M5 Ultra: 5 s 864x480 clip in ~50 s, 40 s at 768x448 — the f…☆30Oct 7, 2026Updated last month
- llama.cpp fork for running Qwen3.8-Flash-Next V3 (95.5 GiB) on a 64 GB Apple Silicon Mac by streaming MoE experts from SSD. Setup guide: …☆13Sep 19, 2026Updated last month
- Community maintained hardware plugin for vLLM on Apple Silicon☆1,991Updated this week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Sushi engine runs very high quality quant model in Apple Silicon, using both STQ and EXL3 format with special tuning technology.☆445Updated this week
- Minimalist repo to do mlx vlm constrained decoding in batch mode☆20Apr 11, 2026Updated 7 months ago
- Raw-Metal inference engine for Qwen3.8-Flash-Next on Apple M5: EXL3 weights, MTP, OpenAI + Anthropic APIs☆13Oct 23, 2026Updated 2 weeks ago
- High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal mode…☆1,654Updated this week
- Realtime TUI and web dashboard for multi-node NVIDIA DGX Spark clusters, with 200G ConnectX-7 RDMA fabric telemetry☆13Oct 24, 2026Updated 2 weeks ago
- Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built …☆8,159Updated this week
- MLX Studio - Easiest way to run LLM's on your Mac. All in one engine.☆990Updated this week
- Splish: a fork of Inco's Splash, tuned for Apple M5 GPUs. Apache-2.0☆33Oct 29, 2026Updated 2 weeks ago
- ⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache…☆796Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- DeepSeek 4 Flash local inference engine for Metal☆97Updated this week
- A native Mac App for LLM fine-tuning on Apple Silicon — fully on-device, fully open source.☆289Oct 27, 2026Updated 2 weeks ago
- lithos-metal: high-performance LLM inference kernels and serving for Apple silicon.☆344Oct 21, 2026Updated 3 weeks ago
- Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.☆32,189Updated this week
- Local LLM Testing & Benchmarking for Apple Silicon☆217Sep 5, 2026Updated 2 months ago
- DS Menu Bar - A Lightweight Menu Bar Control for DwarfStar Server (ds4-server)☆18Nov 4, 2026Updated last week
- A top for local LLMs: memory, paging, GPU and tokens/s for oMLX, Ollama, llama.cpp, vLLM and more☆151Updated this week
Are these results useful?