DeepSeek 4 Flash local inference engine for Metal
☆95Nov 2, 2026Updated this week
Alternatives and similar repositories for ds4-metal
Users that are interested in ds4-metal are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm☆17Oct 22, 2026Updated 2 weeks ago
- Turn the Hacker News front page into local AI art. Powered by mlx-vlm, MFlux, and Apple Silicon.☆35Aug 3, 2026Updated 3 months ago
- LLM Inference Engine for Metal, CUDA and Vulkan.☆1,677Updated this week
- Speeds up TTFT☆23Sep 25, 2026Updated last month
- ☆71Oct 3, 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.
- Qwen3.8-27B EXL3 (4.00 bpw) + DFlash2 speculative decoding for ExLlamaV3, validated at 262k context on a 24 GB RTX 3090☆25Sep 20, 2026Updated last month
- Supply-chain auditor for (abliterated) GGUF & .safetensor models: chat-template tamper detection, tensor fingerprints, plain-language rep…☆12Oct 15, 2026Updated 3 weeks ago
- DSpark-style speculative decoding draft head for Qwen3.6-27B AEON: training recipe, paired eval harness, vLLM patches. +11% serve tok/s v…☆14Jul 2, 2026Updated 4 months ago
- An experimental artificial life platform for embodied synthetic cognition and procedural morphogenesis, from individual beings to worlds …☆15Updated this week
- Qwen3.8-27B on one DGX Spark GB10: DFlash 2 for 65 tok/s C1 and 120 C4; EAGLE 3/1/4 for ~191 C8, ~330 C16 and ~535 C32; native 262K, pinn…☆13Oct 6, 2026Updated last month
- See where local inference loses speed on Apple Silicon under Linux☆14Updated this week
- Dynamic Orchestrator Agent (DOA)☆12Jun 1, 2025Updated last year
- MosaicMem in Rust - Hybrid Spatial Memory for Video World Models☆19Mar 26, 2026Updated 7 months ago
- Give DeepSeek V4 Flash eyes. OpenAI-compatible shim + tiny local VLM. Point any harness at one URL and your text-only model accepts image…☆30Aug 9, 2026Updated 2 months ago
- 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.
- Hardware-pinned, verified recipes for serving large open-weight LLMs. Every number has a method.☆26Updated this week
- Sushi engine runs very high quality quant model in Apple Silicon, using both STQ and EXL3 format with special tuning technology.☆421Updated this week
- 🌑 Native macOS menu bar app for Darkbloom providers — live status, earnings, and provider control☆25Aug 26, 2026Updated 2 months ago
- Idol: a single image to 3D Gaussians. Inference SDK and demo.☆19Updated this week
- Run one AI agent as the orchestrator of your whole workspace, inside the Orca ADE, on the CLI subscription you already pay for. No API ke…☆19Oct 28, 2026Updated last week
- An open standard for AI registries☆158Updated this week
- MiniMax-H3 (video + synchronized audio, 33B) on diffusers — 9.7s per still, 44.2s per 5s clip on 48GB, with every speedup verified byte-i…☆20Oct 13, 2026Updated 3 weeks ago
- Wan2.2 for Mac.☆17Oct 3, 2025Updated last year
- Convert and Run Exl3 format LLM quant on Apple Silicon.☆60Aug 24, 2026Updated 2 months 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.
- Serve DeepSeek-V4-Flash-Vision EXL3 MixedK (full 256 experts) on one NVIDIA DGX Spark with vLLM — recipe, loader patches, and receipts☆14Sep 7, 2026Updated last month
- Your Claude, learned locally SLM fine tuned on your Claude Code sessions, served for OpenCode/Cursor/Codex☆18Updated this week
- An ultra-fast Prime Agent fork designed to orchestrate concurrent sub-agents and execute long-running coding tasks without the Python lat…☆18Oct 16, 2026Updated 3 weeks ago
- Cake Build addin for managing (simctl) Apple iOS/watchOS/appleTV simulators☆15Dec 8, 2022Updated 3 years ago
- 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…☆2,673Updated this week
- Qwen3.8-27B NVFP4 on SGLang (DGX Spark / SM121): official image pin, native DSpark/EAGLE click-run, matched evals☆21Aug 19, 2026Updated 2 months ago
- Run one local MLX model across Apple Silicon Macs on macOS and on Omarchy Linux, served as one OpenAI-compatible endpoint☆24Updated this week
- Real-time talking character on a single RTX 5090 — LTX-2.5 22B + local LLM + TTS, fully local. First video ~2.6s after Enter.☆42Oct 19, 2026Updated 2 weeks ago
- ☆54Oct 20, 2026Updated 2 weeks 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.
- Provides classes for token validations for Yii2 framework☆10Feb 8, 2016Updated 10 years ago
- ☆13Apr 28, 2026Updated 6 months ago
- Blazor, ASP.NET Core, Xamarin, .NET Standard <3☆14Dec 8, 2022Updated 3 years ago
- ☆65Sep 7, 2026Updated last month
- ☆12Nov 22, 2025Updated 11 months ago
- Run DeepSeek V4-Flash (~100B MoE) on a 48GB Apple Silicon Mac via SSD expert-streaming — a custom MLX offload engine. ~4.5-5 tok/s.☆10Jul 4, 2026Updated 4 months ago
- LLM quantization optimizer☆23Aug 20, 2026Updated 2 months ago