250M parameter language model. 100M-token offline context. 60 MB deployment, 400 tok/s on a laptop CPU.
☆108Oct 15, 2026Updated last month
Alternatives and similar repositories for SHADOW-250M-Instruct
Users that are interested in SHADOW-250M-Instruct are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- SHADOW 50M Instruct: a proof of concept. 44M ternary parameters, exact circuits inside the model, memory on disk, 19.8 MB, offline on a C…☆35Oct 19, 2026Updated last month
- Differential-KV (DKV) is a sparse KV-cache inference runtime designed for high-efficiency, memory-bounded long-context Large Language Mod…☆21Oct 30, 2026Updated 2 weeks ago
- ☆29Oct 11, 2026Updated last month
- mandelbrot set in zig☆12Sep 13, 2022Updated 4 years ago
- A compiler that transforms computation graphs into the weights of a transformer☆32Aug 9, 2026Updated 3 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.
- Implementation of build an LLM from scratch by Sebastian Raschka.☆23Jan 22, 2026Updated 9 months ago
- Exploring Ultrafast machine learning on FPGAs via Kolmogorov-Arnold Networks☆18Jun 15, 2026Updated 5 months ago
- 249M-param MoE transformer built from scratch in PyTorch. GQA, RoPE, SwiGLU, sparse MoE with 3 aux losses, AMP training loop no Trainer a…☆19May 22, 2026Updated 5 months ago
- A DSP Toolkit for PyTorch☆12Jul 2, 2025Updated last year
- A tool-calling layer, not a language model — your schemas in, validated calls out, at 48M parameters. Malformed JSON, invented parameter …☆12Aug 25, 2026Updated 2 months ago
- ☆51Oct 1, 2025Updated last year
- Typed decisions in one forward pass: Smol 421M, Big 4B and Nagi-HUGE 12B. Reproducible four-system benchmark.☆13Oct 13, 2026Updated last month
- 🥷 Give your codebase a black belt. Local code intelligence, security analysis, and compiler-backed facts for humans and AI.☆26Updated this week
- ☆50Updated this week
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- ☆10Oct 22, 2026Updated 3 weeks ago
- An open engine for 2004 RPG Discord Times (Времена раздора): play it with your own copy of the game.☆25Updated this week
- ☆15Apr 22, 2025Updated last year
- An endless first-person backrooms game, presented as a damaged VHS recording. Next.js, Three.js, Rapier, WebGPU.☆22Sep 28, 2026Updated last month
- 🧠 Multi-agent AI development environment powered by OpenRouter. 5 specialized AI agents work in parallel with automatic build-test-fix c…☆16Aug 25, 2026Updated 2 months ago
- How hard can it be to implement a diffusion language model by hand? Easier than I thought, actually.☆22Jun 29, 2026Updated 4 months ago
- REQL – A graph-native code index engine for agents. Scans Python, TypeScript, Go, Rust, Java, and 30+ languages to build a property graph…☆18Updated this week
- world's stupidest moe llm in 103M parameters☆20Jul 18, 2025Updated last year
- Sovol Zero profiles for OrcaSlicer, PrusaSlicer and SuperSlicer, plus optional Klipper macros for faster chamber heating and a quieter ex…☆17Updated this week
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- A proof of concept model based on Llama 3.1-8B, featuring reasoning capabilities in Bulgarian.☆12Feb 9, 2025Updated last year
- Sib is git-based (literally) llm client☆11Oct 5, 2026Updated last month
- Live terminal artifacts☆11Aug 20, 2026Updated 2 months ago
- A token-efficient code map for AI coding agents: outline, call graph, "who calls this?" and impact analysis without reading whole files. …☆16Updated this week
- ☆14Mar 8, 2023Updated 3 years ago
- On-device voice models and SDK: voice isolation, wake words, voice activity and voiceprints. In the browser (WebAssembly), Python, Androi…☆77Nov 5, 2026Updated last week
- Generalist Multitask Transformer Encoders☆137Nov 2, 2026Updated 2 weeks ago
- Variational Autoencoder implemented in Tensorflow.js☆11Jun 6, 2018Updated 8 years ago
- DOOM compiled to a transformer☆14Aug 13, 2026Updated 3 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.
- [ACCV 2026 Oral] Official implementation of "REBASE: Reference-Background Subspace Elimination for Training-Free In-Context Segmentation"…☆15Oct 13, 2026Updated last month
- A taskwarrior-style command line for Org mode's agenda: short IDs, one-line actions, and your running Emacs doing all the Org work.☆15Oct 28, 2026Updated 3 weeks ago
- ☆14Oct 13, 2026Updated last month
- ZONESTAR Z9 3D printer Documents☆15Nov 20, 2024Updated last year
- Custom firmware and a self-hosted voice server for the M5Stack StackChan (CoreS3 with two Feetech SCS0009 servos). It replaces the stock …☆31Oct 22, 2026Updated 3 weeks ago
- Task Manager on steroids: a Windows task manager that stays responsive under load and shows who is doing what, and why. Kernel tracing, s…☆19Updated this week
- Self-hosted Qwen3.8-27B (FP8) inference with vLLM, KServe and Envoy AI Gateway on RTX 6000 PRo or 2× RTX 4080 Super☆18Sep 2, 2026Updated 2 months ago
Are these results useful?