cyberneurova-DeepSeek-V4-Flash-abliterated-aligned local inference engine with M5 Metal support
☆38Oct 22, 2026Updated 2 weeks ago
Alternatives and similar repositories for ds4
Users that are interested in ds4 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 備用的萌典(moedict pwa & app, Quasar used)☆12Jul 31, 2025Updated last year
- Giant MoE models on a single consumer GPU by streaming experts from SSD. CUDA fork of antirez/ds4: runs GLM-5.2 (743B), Tencent Hy3 (295B…☆40Jul 12, 2026Updated 3 months ago
- English guide + one-command patcher for the vLLM spin-wait bug that overheats NVIDIA DGX Spark / GB10. Credit: nacyot. CPU cores spin at …☆24Aug 17, 2026Updated 2 months ago
- auto mount omniauth-facebook☆10Dec 24, 2013Updated 12 years ago
- 萌典cloudFlare worker複刻版, 整合 React + Vite + Wrangler + Functions + SSR 支援☆13Updated this week
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- ☆14Oct 20, 2025Updated last year
- Qwen3.8 Flash-Next (NVFP4) on NVIDIA Flare for one DGX Spark / ASUS GX10: greedy, 8-agent speculative decoding, mixed prefill☆14Updated this week
- Private, on-device bilingual captions and assisted conversation for iPhone, iPad, and Mac.☆15Oct 1, 2026Updated last month
- 適合自學親子使用的自由數學教材教法，以全中文編輯☆18Updated this week
- Hardened Mode for Nginx☆27Mar 8, 2022Updated 4 years ago
- 島島阿學官方網站☆12Updated this week
- Boo, a ghost-faced audio/visual agent you talk to from your phone: speech in and out, camera, hand tracking, memory and a tool-using back…☆14Oct 30, 2026Updated last week
- Open quantization tooling for TurboQuant-style low-bit LLM releases, stock GGUF deployment, and Apple Silicon runtime experiments.☆10May 5, 2026Updated 6 months ago
- glm53-flash recipe for tp=2 GB10☆18Oct 29, 2026Updated last week
- 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.
- Run CyberNeurova-DeepSeek-V4-Flash-abliterated-GGUF locally on metal right from within Pi☆317Updated this week
- Towards Total Recall in Industrial Anomaly Detection☆10Jul 9, 2021Updated 5 years ago
- Uncensored DeepSeek-V4.1-Flash-1017 on 2x DGX Spark: refusals 94 to 6, same answers as DeepSeek's API, 2,008 tok/s prefill at 128K, 113 t…☆47Oct 27, 2026Updated last week
- Convert PDF to markdown with lightonai/LightOnOCR-2-1B☆13Jan 23, 2026Updated 9 months ago
- Qwen3.8-Flash-Next on two DGX Sparks with TensorFold☆50Oct 26, 2026Updated last week
- turn qwen 3.6 27B-> AR -> diffusion (opendllm + d3llm)☆15Jun 11, 2026Updated 4 months ago
- Root repository for Plurality: Technology for Collaborative Diversity and Democracy by Audrey Tang and E. Glen Weyl☆20Jul 3, 2026Updated 4 months ago
- LLM quantization optimizer☆23Aug 20, 2026Updated 2 months ago
- Enhanced MCP server for Bloomberg Terminal — BDP/BDH/BDS/BQL/TA with 18 tools, caching, and dynamic screening. Based on tallinn102/bloomb…☆26Apr 19, 2026Updated 6 months ago
- 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.
- Experimental implementation of DeepSeek v4 flaash in llama.cpp☆24Apr 30, 2026Updated 6 months ago
- Running MiniMax-M2.5 on a Nvidia DGX Spark with OpenCode on the remote machine☆12Feb 19, 2026Updated 8 months ago
- Portable personal advisor OS built from Agent Skills☆13Aug 12, 2026Updated 2 months ago
- MCP-first local context retrieval for AI coding tools — BM25 over markdown + SQLite learned memory. Works with Claude Code, Codex, Gemini…☆14May 5, 2026Updated 6 months ago
- MCP server for 3D-printable CAD modeling with build123d, targeting Bambu Lab X1C☆14Mar 18, 2026Updated 7 months ago
- vLLM Qwen 3.6-27B (AWQ-INT4) + DFlash speculative decoding on AMD Strix Halo (gfx1151 iGPU, 128 GB UMA, ROCm 7.13). 24.8 t/s single-strea…☆53May 10, 2026Updated 5 months ago
- The best benchmark for LLMs on Apple's MLX framework knowledge and coding tasks.☆38Jun 12, 2026Updated 4 months ago
- Tested MiaAI-based DeepSeek V4 Flash speed profile for two ASUS GX10s: pinned patch, settings, and benchmark helper.☆15Sep 5, 2026Updated 2 months ago
- A cross-platform printer AI MCP server that supports Windows, macOS, and Linux systems, providing printer management, status queries, and…☆14Mar 10, 2026Updated 7 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.
- ☆17Jan 12, 2026Updated 9 months ago
- CUDA Blackwell performance fork of antirez/ds4 (DeepSeek-V4-Flash): ~4x prefill, ~1.5x decode, continuous batching, weight server, DSpark☆77Oct 26, 2026Updated last week
- Cross-platform pure C+GPU inference for Llama 2-family, Mistral Nemo, GPT-2, Gemma-3n, Qwen 3.5+, GPT-NeoX, StableLM, GLM-5.3 GGUFs. Enha…☆15Updated this week
- an MCP for querying the EVM☆12Apr 1, 2025Updated last year
- Simple single-video YouTube MP3/MP4 downloader for Windows☆13Oct 28, 2026Updated last week
- Chiron fonts modified for code-mixing subtitles☆12Jan 20, 2026Updated 9 months ago
- ☆13Oct 28, 2025Updated last year