DeepSeek-V4-Flash-0731 284B inference in ~25 GB of RAM / Qwen3.8-Next-Flash inference in ~15 GB of RAM on any M-series MacBook
☆143Oct 16, 2026Updated this week
Alternatives and similar repositories for Whallm
Users that are interested in Whallm 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 a 105 GB AI model on a Mac that can't hold it. Slotstream streams Qwen3.8-Flash-Next (125B mixture of experts) from your SSD and cach…☆476Updated this week
- Convert and Run Exl3 format LLM quant on Apple Silicon.☆58Aug 24, 2026Updated last month
- Semark converts PDFs, Office files, HTML, and images into RAG-ready semantic Markdown using MinerU and VLM/LLM review, with chunks, sourc…☆27Aug 14, 2026Updated 2 months ago
- Official Codebase of 3DCodeVerse☆92Updated this week
- The open-source trading harness for Claude Code / Codex agents.☆237Oct 8, 2026Updated last week
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- MCP server for controlling Google Flow via browser automation (Playwright + CDP)☆105May 31, 2026Updated 4 months ago
- PaperRead｜繁體中文論文閱讀、研究探索與知識整理工作區☆270Updated this week
- Minimalist repo to do mlx vlm constrained decoding in batch mode☆19Apr 11, 2026Updated 6 months ago
- Up to 4× faster LLM decoding on Apple Silicon, lossless. Native MLX port of DeepSeek's DSpark & z-lab's DFlash speculative decoding — Gem…☆719Oct 5, 2026Updated last week
- Cartograph turns any GitHub repo into an interactive dependency map by parsing real code to analyze structure, trace imports, calculate b…☆84Oct 2, 2026Updated 2 weeks ago
- Most coding agents grep and glob raw source into LLM's context window and hope the model is smart. Benzi compiles your codebase into a ma…☆165Updated this week
- The quality-ranked discovery engine for AI coding skills, plugins and MCP servers across Claude Code, Codex, Cursor, Windsurf, Cline and …☆78Updated this week
- 🕸️ E.V. — Peter Parker's homemade AI from Spider-Man: Brand New Day, running locally on YOUR PC. Voice assistant + cyber HUD, real PC co…☆61Aug 10, 2026Updated 2 months ago
- Claude Code mod: hand a long session off to a fresh one with a structured brief, instead of auto-compacting☆77Oct 4, 2026Updated last week
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Inkwell: a small app, the Super Simple Software Factory that builds it, and the rebootable sandbox system that runs both on a throwaway V…☆161Aug 9, 2026Updated 2 months ago
- Communicating with NATS using the HTTP protocol.☆19Jun 22, 2024Updated 2 years ago
- Nimic allows using pure Python as a systems language with AOT compilation. It provides systems-level functionality directly within CPytho…☆42Updated this week
- A local MITM proxy that lets you control TLS fingerprints (JA3/JA4), HTTP/2 fingerprints, HTTP header order, and User-Agent — all from a …☆41Updated this week
- Semantic, format-aware diff for config & structured-data files (JSON, YAML, TOML, INI, .env, .properties, CSV, XML). See what actually ch…☆41Sep 22, 2026Updated 3 weeks ago
- AutoMapper website☆14Aug 19, 2020Updated 6 years ago
- Finds the AI papers 28 tech companies put on arXiv over any date range, and splits lead authorship from bylines. A SKILL.md agent skill —…☆220Sep 1, 2026Updated last month
- ☆41Aug 16, 2026Updated 2 months ago
- What Claude Code is doing between your prompt and its answer, drawn live from the logs it already writes: every model call, every tool, e…☆47Updated this 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.
- Turn any video into a Mixamo-rig animation - GVHMR estimator, spec-driven retarget, FK apply in Blender via MCP. Works with any Mixamo ch…☆375Sep 26, 2026Updated 3 weeks ago
- Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization☆12Dec 3, 2024Updated last year
- Synapse — Temporal knowledge graph memory for AI agents. Self-hosted FalkorDB + Graphiti with hippocampus-layer memory management.☆76Updated this week
- Fast, local, simple voice typing for macOS.☆80Sep 29, 2026Updated 2 weeks ago
- Interactive canvas for taking an LLM apart tensor by tensor: measured INT8/INT4/FP8 error, distributions, spectra and outlier channels fo…☆75Sep 2, 2026Updated last month
- 一个本地网关，把 Tabbit Web Chat 能力桥接成 API 给外部调用，白嫖最新的大模型 GPT-5.5、 Opus-4.8 等。| A local gateway that turns Tabbit into an API, letting you freel…☆109Aug 18, 2026Updated last month
- A small in-memory key value database for rust☆14Jun 8, 2023Updated 3 years ago
- ☆43Aug 10, 2026Updated 2 months ago
- A QGIS plugin for leafmap☆22Oct 5, 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.
- UnoDOS — active development (the forward, contract-driven line; master carries the pc64 x86-64/UEFI world). Frozen legacy (archived): hmo…☆33Oct 9, 2026Updated last week
- Archived — mnml evolved into Verso: https://github.com/linuz90/obsidian-verso☆85Aug 22, 2026Updated last month
- Open-source options gamma exposure (GEX) & positioning dashboard — dealer GEX, max pain, open interest, IV surface. Self-hosted, Docker, …☆86Updated this week
- 基于.net core2.1 搭建的框架的中小型项目框架,sql server数据库,同时支持,mysql数据库,,,需要自己稍微扩展下,,,可以擦模考sql server的实现 迁移文件已经生成,可以直接运行即可跑起来. 结合docker发布可以参考这里: https…☆13Dec 4, 2018Updated 7 years ago
- Useful template literal tag for create html strings in ES2015+☆13Jun 29, 2026Updated 3 months ago
- Configuration, benchmarking scripts, and raw data for serverless cold start benchmarks.☆17Jul 24, 2024Updated 2 years ago
- Qwen3.8-Flash-Next on Apple Silicon: an MLX engine that reads Strata's GGUF files and speaks its line protocol (unofficial)☆97Updated this week