DeepSeek-V4 in C99, streamed off NVMe. Runs the 284B Flash checkpoint from 3.2 GB of RAM, 1.81 s/token with a GPU, verified against PyTorch to 2.9e-6.
☆22Aug 25, 2026Updated last month
Alternatives and similar repositories for deepseek-v4-in-c
Users that are interested in deepseek-v4-in-c are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Qwen3.8-27B on one laptop CPU: up to 2.52 token/s, 8 GB tested, no runtime accuracy loss. Native OpenAI-compatible API with function tool…☆21Sep 9, 2026Updated last month
- The best model under 200B at near 10 token/s exact batch throughput on a single laptop CPU, with an automatic 8 GB RAM path. Native C, no…☆23Sep 9, 2026Updated last month
- Crow — a local AI agent, not a chat box: 30 tools, MCP, memory, skills, goals, subagents, vision, and image generation and editing with Q…☆37Updated this week
- Secure MCP access to local repositories — without shell, Git, or arbitrary writes.☆29Aug 31, 2026Updated last month
- A local-first Windows AI assistant with a multi-model council pipeline, Python sandbox, web search, and cloud AI support. Free. Private. …☆29Oct 12, 2026Updated last 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.
- DeepSeek-V4.1-Flash on 2x NVIDIA DGX Spark with the TensorFold engine: 1.8-1.9x code, 2.5x multi-stream, 1.7-1.95x prefill vs the vLLM ki…☆77Updated this week
- 6800% faster "os" module replacement. A drop-in replacement for Python's standard 'OS' module. Fully-rewritten, optimized, and speeded-up…☆18Feb 20, 2023Updated 3 years ago
- 🏕️ A Gemini-to-Gopher proxy that bridges the smolweb to even more smolweb☆11Mar 4, 2026Updated 7 months ago
- smol is a smol agent☆137Aug 15, 2026Updated 2 months ago
- ☆11Dec 27, 2023Updated 2 years ago
- Deterministic, read-only static auditor for GGUF models: behavioral chat-template backdoors + SSTI, tokenizer, config, and model-card sur…☆28Oct 1, 2026Updated 2 weeks ago
- A simple socket server for jailbroken PS5s that redirects /dev/klog to sockets connected on port 3232☆11Apr 10, 2024Updated 2 years ago
- A local-first coding agent that doesn't take "done" on faith: the engine keeps the run going until the project's own tests pass, and ever…☆82Sep 22, 2026Updated 3 weeks ago
- PLE n-gram knowledge injector for Qwen3.8-Flash-Next☆21Sep 3, 2026Updated last month
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Run MoE models bigger than your RAM. Frontier-size MoE on a phone, laptop, edge. Lossless, on stock llama.cpp. An adaptive streaming opti…☆633Updated this week
- Serve the official Ling-3.0-flash INT4 on one NVIDIA DGX Spark, 38.7 tok/s, faster than the community GGUF. Recipe, watchdog, benchmarks.☆26Aug 29, 2026Updated last month
- Angel - a symmetrical staggered ergonomic keyboard.☆13Jan 27, 2021Updated 5 years ago
- A Los Angeles Times theme for Python's Altair statistical visualization library☆12May 20, 2021Updated 5 years ago
- Showing how to integrate CMake, C++, and pybind11☆11May 1, 2018Updated 8 years ago
- Simple portage of Enable/disable Updates from the PS4 collective scene☆13Feb 28, 2023Updated 3 years ago
- Microbenchmarks showing relative performance of different Python functions/patterns.☆13Oct 3, 2025Updated last year
- A wallet of AI agents that use real tools and ask each other when a question isn't theirs. Runs on your computer; the model is your choic…☆31Sep 4, 2026Updated last month
- 3D Minkowski Tensor Package☆10May 7, 2026Updated 5 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.
- ☆10Aug 29, 2021Updated 5 years ago
- 3D point cloud registration tool☆11Feb 8, 2021Updated 5 years ago
- Compile JSON to BIND zone files automatically☆14Nov 26, 2025Updated 10 months ago
- ☆17Aug 2, 2024Updated 2 years ago
- LLM inference in C/C++☆26Sep 17, 2026Updated last month
- An experimental webkit-based kernel exploit (Arb. R/W) for the PS5 on <= 4.51FW☆15Apr 20, 2025Updated last year
- Composable Python reinforcement-learning library for Trackmania 2020: training, evaluation, custom models and game integration.☆27Updated this week
- FileFlows is a file processing application that can execute actions against a file in a tree flow structure.☆18Jan 31, 2023Updated 3 years ago
- A vibe coded webUI for easily loading and managing models run by llama.cpp☆20Updated 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.
- Gradio chat interface for FastMLX☆11Sep 21, 2026Updated 3 weeks ago
- ISONGraph is a multi-language property graph library designed specifically for LLM and AI applications. It provides the most token-effici…☆17Sep 5, 2026Updated last month
- Custom node to load models in int8-(convrot) & now int4-/convrot) for speed gains on AMD GPU's with ROCM. (should work with nvidia gpus …☆47Updated this week
- Get paid while AI thinks.☆84Oct 5, 2026Updated 2 weeks ago
- WebServer+Wifi Repeater+Fake DNS Server to Host PS5 Exploits on ESP8266/ESP32☆15Sep 24, 2024Updated 2 years ago
- A fortnite 12.41 gameserver☆13Dec 24, 2024Updated last year
- Source-only Rust/Bevy Skate 3 preservation project with owned-ISO asset setup☆33Sep 3, 2026Updated last month