A 49M-parameter Kimi K3-inspired language model trainable on one 8GB GPU
☆101Jul 28, 2026Updated 3 months ago
Alternatives and similar repositories for smol-kimi-k3
Users that are interested in smol-kimi-k3 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆11Jun 29, 2026Updated 4 months ago
- The pretraining scaffold behind 'Pretraining a Mini Kimi K3' (free book): six-source HF data mix, benchmark decontamination, tokenizer, W…☆37Aug 20, 2026Updated 2 months ago
- ☆11Oct 25, 2025Updated last year
- A compact, readable PyTorch reference implementation of the DeepSeek-V4 architecture (Flash and Pro), in the spirit of nanoGPT. ~4,300 LO…☆19Aug 14, 2026Updated 3 months ago
- Kimi CLI Zed extension.☆14Jan 20, 2026Updated 9 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Diffeomorphic Information Neural Estimation (DINE) - AAAI 2023☆10Jul 3, 2023Updated 3 years ago
- Implementation of VisionLLaMA from the paper: "VisionLLaMA: A Unified LLaMA Interface for Vision Tasks" in PyTorch and Zeta☆15Nov 11, 2024Updated 2 years ago
- ☆13Sep 13, 2023Updated 3 years ago
- Scripts to automatically sync Claude Code generated TODO to TaskWarrior☆17Jun 22, 2025Updated last year
- Official code for the paper: "Simple LLM Baselines are Competitive for Model Diffing"☆11Feb 13, 2026Updated 9 months ago
- an MCP for querying the EVM☆12Apr 1, 2025Updated last year
- Code and experiments using the optimal solution to the flow-matching training objective.☆13Jun 14, 2025Updated last year
- Deployment & experimentation of LLM inference at production scale (P/D disaggregation, KV offloading, parallelism, and autoscaling).☆65Sep 26, 2026Updated last month
- Concepts in SWE RL Training☆13Jul 31, 2026Updated 3 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- GLM-5.2, a 744 billion parameter mixture of experts model, in a pure C inference engine: quantized to int4, experts streamed from disk, d…☆77Jul 15, 2026Updated 3 months ago
- Testing LLM reasoning abilities with family relationship quizzes.☆62Jan 28, 2025Updated last year
- ☆14Sep 10, 2023Updated 3 years ago
- Waste Segregation @HackBash2021 : ML based deployed waste segregation web app☆12Apr 8, 2021Updated 5 years ago
- ☆14Apr 16, 2025Updated last year
- An open source platform to annotate data for Large language models - at scale☆16Oct 31, 2025Updated last year
- An interactive F1 race simulator using Reinforcement Learning (PPO, Q-learning) and Streamlit to optimize pit stop strategies based on dy…☆16Oct 8, 2025Updated last year
- Fine-tune Mistral-7b on the Enlighten codebase☆29Feb 6, 2024Updated 2 years ago
- LangGraph tutorial series — 10 progressive notebooks from beginner to expert☆18May 16, 2026Updated 5 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Assessing Boltz-2 performance for the binding classification of docking hits☆11Jan 5, 2026Updated 10 months ago
- Encountering 14 different Naive RAG fails and using KG to solve it☆34Dec 4, 2025Updated 11 months ago
- ☆11Mar 29, 2025Updated last year
- Instant Neural Graphics Primitives from scratch, zero dependencies. Learning by doing.☆10Aug 18, 2023Updated 3 years ago
- Cancer Skin Classification (HAM10000) using Vision Transformer (ViT)☆13Apr 29, 2023Updated 3 years ago
- Serial port MCP server for Claude Code, Codex, Opencode and AI agents. Reliable UART/USB-serial access for embedded development.☆20Updated this week
- Config files for my GitHub profile.☆12Updated this week
- NLP command-line assistant powered by OpenAI☆21Jan 27, 2024Updated 2 years ago
- Groq-Whisper Fast Transcription App built using Groq API and Streamlit.☆26Sep 23, 2024Updated 2 years 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.
- ☆29Apr 4, 2025Updated last year
- ☆14Apr 8, 2026Updated 7 months ago
- Data pipeline for HRM-Text pretraining☆73Sep 23, 2026Updated last month
- Durable, git-backed working-state for coding agents: append-only ledgers with identity, evidence, cursors, and agent-curated roll-ups☆14Aug 20, 2026Updated 2 months ago
- Qwen3.6 27B × DFlash — 30-35 tok/s on NVIDIA DGX Spark (GB10) - LLama.Cpp☆17May 2, 2026Updated 6 months ago
- LocaLeJEPA: JEPA self-supervised learning that matches the embedding distribution locally, in k-means neighborhoods, instead of globally,…☆15Nov 7, 2026Updated last week
- ☆14Updated this week
Are these results useful?