TurboQuant llama.cpp fork with optimized turbo4 kernels for Gemma 4 D=256/512 heads — lazy K/V, batch decode, warp-cooperative write. 120 t/s with 3.8x KV compression on RTX 3090.
☆37Apr 5, 2026Updated 6 months ago
Alternatives and similar repositories for llama-cpp-turboquant-gemma4
Users that are interested in llama-cpp-turboquant-gemma4 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- HIP/ROCm fork optimized for AMD RDNA2 (gfx1030) with PrismML Q1_0_G128 1-bit quant support, RotorQuant, TurboQuant, EAGLE3 and P-EAGLE sp…☆26Jun 23, 2026Updated 4 months ago
- ☆41Mar 31, 2026Updated 7 months ago
- MLX benchmark: Gemma 4 + Qwen 3.5 on Apple Silicon with TurboQuant KV cache☆22Apr 6, 2026Updated 6 months ago
- Benchmarks, compose files, and findings for running Qwen3.6 (27B dense + 35B-A3B MoE) on 4× RTX 3090. vLLM/AWQ vs llama.cpp/GGUF, MTP spe…☆21Aug 15, 2026Updated 2 months ago
- DeepSeek Harness (DSH) 跨会话记忆插件：对话模型边干边记的 Markdown 项目记忆，支持专题文件渐进式披露、可选后台静默蒸馏、按项目隔离与热更新设置面板。机制对齐 Claude Code auto memory。 | Agent-maintaine…☆17Sep 30, 2026Updated last month
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Mirror from gitlab☆11Jan 9, 2021Updated 5 years ago
- Various fonts i've drawn.☆11May 29, 2021Updated 5 years ago
- Qwen4-Exp (Qwen3.8-Flash-Next) SWA + MTP + PLE-on-iswa — bounded deep-context decode w/ long-range recall, TBQ4 4.25 bpv KV, DSpark + Rot…☆95Sep 24, 2026Updated last month
- A terminal-based renderer for OpenGL shaders. Like Shadertoy, but in the terminal.☆12Sep 24, 2023Updated 3 years ago
- ☆12Dec 11, 2022Updated 3 years ago
- A light-weight curses-like header-only library. Good for terminal-based games and such.☆11Aug 10, 2026Updated 2 months ago
- Unsupported SNES emulator for multicore ARM Cortex A7,A9,A15,A53 Linux platforms.☆16Aug 23, 2026Updated 2 months ago
- Research / Toy Renderer☆11Jul 11, 2026Updated 3 months ago
- gorynlich, 2d platform dungeon romp☆13Nov 8, 2021Updated 4 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- nQuantGpp includes top 10 color quantization algorithms for g++ producing high quality optimized images.☆13Oct 15, 2026Updated 2 weeks ago
- A standalone C++ library and toolkit for running neural text-to-speech models in GGUF format, with no Python dependencies.☆11Oct 16, 2026Updated 2 weeks ago
- Atrinik multi-repository development workspace and component coordinator☆31Updated this week
- Truly local AI agent running entirely on your hardware. Autonomous tasks, file & shell access, Telegram updates, cron jobs, and RPG progr…☆15Sep 28, 2026Updated last month
- An easy-to-script bot written in PHP which attempts to link IRC with SQL database, allowing for integration between platforms☆10Sep 8, 2021Updated 5 years ago
- mining_web☆11Mar 1, 2022Updated 4 years ago
- Browser extension for private p2p chat with audio,video, screensharing.☆16Oct 14, 2026Updated 2 weeks ago
- A desert strike clone, in 3d☆12Jan 8, 2015Updated 11 years ago
- AlsoAsked MCP Server☆15Jun 9, 2025Updated last year
- 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.
- The l4t linux kernel☆10Dec 5, 2018Updated 7 years ago
- Local AI workstation — discover, run, chat, benchmark, and generate images from open-weight models. DFlash/DDTree speculative decoding, T…☆25Oct 22, 2026Updated last week
- VDPAU backend driver for NVIDIA Tegra 20/30/114 SoCs☆16May 15, 2022Updated 4 years ago
- ☆18Feb 10, 2020Updated 6 years ago
- Video plugin for Mupen64Plus v2.0, based on the Arachnoid plugin for Project64.☆20Jun 23, 2026Updated 4 months ago
- Protobuf messages in a bottle☆10Sep 15, 2026Updated last month
- llama.cpp fork with TurboQuant WHT-rotated KV cache & weight compression + Gemma 4 MTP and Qwen 3.6 NextN speculative decoding (+30-50% t…☆432Updated this week
- jfbterm☆10May 7, 2015Updated 11 years ago
- ☆10Sep 8, 2026Updated last month
- 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.
- VAAPI backend for Tegra☆10Oct 20, 2021Updated 5 years ago
- ⠙⠕⠞⠊⠋⠽ / convert bytes to braille and back again☆12May 14, 2018Updated 8 years ago
- Rust Shaicoin Miner☆10Dec 27, 2025Updated 10 months ago
- Rust implementation of POST proving☆13Dec 15, 2025Updated 10 months ago
- One serving daemon for local LLM inference — across runtimes and machines.☆19Updated this week
- ☆12Dec 26, 2023Updated 2 years ago
- Original and reverse-engineered music players☆15Jun 24, 2023Updated 3 years ago