Quasar is an inference engine for Qwen3.6-27B-MTP / Qwen3.8-27B on consumer NVIDIA cards as well as Apple Silicon, in the spirit of antirez/ds4
☆52Nov 5, 2026Updated this week
Alternatives and similar repositories for q27
Users that are interested in q27 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- High-performance single-GPU inference for selected model checkpoints and GPUs.☆24Oct 13, 2026Updated 3 weeks ago
- Utility scripts to quantize models in optimal ComfyUI formata.☆34Aug 21, 2026Updated 2 months ago
- Shape Shifting Softwares☆12Oct 10, 2026Updated 3 weeks ago
- Inference RWKV v7 in pure C.☆47Oct 10, 2025Updated last year
- ☆13Mar 27, 2026Updated 7 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.
- Open-source SM120 (Blackwell) SASS assembler — encode, schedule & assemble GPU machine code, including all tensor-core instructions.☆13Updated this week
- Keep Pi conversation separate from tool output and agent activity.☆14Updated this week
- Free local guardrail for AI coding agents: every tool_call judged on-device (regex + Laya), allow/review/block☆37Updated this week
- Calibration-free OrbitQuant for transformer backbones, with Hugging Face integration and packed CUDA/Metal inference☆15Updated this week
- View token usage, costs, and rate-limit metrics from Codex and Claude Code sessions☆16Oct 12, 2026Updated 3 weeks ago
- LLM inference in C/C++☆12Oct 18, 2026Updated 3 weeks ago
- Repairs predictable tool-call mistakes that often derail open weight models. Supports integration with other extensions' custom tools.☆13Jul 21, 2026Updated 3 months ago
- Qwen and DeepSeek low-VRAM LoRA training with GGUF base model, compatible with Transformers and PEFT☆22Updated this week
- ☆134Oct 31, 2026Updated last week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- RocketLLama. Fork off LLama cpp that newly scales 2-20x now also on big models not fully fitting in vram on even just 2 gpus☆16Updated this week
- wrapper for Hunyuan-PromptEnhancer☆14Oct 10, 2025Updated last year
- ☆15Jan 16, 2026Updated 9 months ago
- One-stop on-device diffusion image-generation engine for iOS / macOS / visionOS. Embeds stable-diffusion.cpp + ggml-metal behind a tight …☆22Updated this week
- Graph-based static analysis tool☆35Aug 24, 2026Updated 2 months ago
- ☆21Oct 21, 2026Updated 2 weeks ago
- One line of NInfer for the Blackwell, Ada Lovelace, Ampere, Turing and Volta NVIDIA GPUs, consolidated from the forks that carry it: GGUF…☆201Updated this week
- IMMA-based **FP8-as-storage** GEMM experiments for Ampere (sm_86 / RTX 3090 Ti).☆28Jan 30, 2026Updated 9 months ago
- A powerful, adaptive system optimizer that automatically generates optimized kernel parameters for Linux systems. This tool detects your …☆14Oct 18, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆16Jul 12, 2026Updated 3 months ago
- ☆14Apr 5, 2026Updated 7 months ago
- High-performance single-GPU inference for selected model checkpoints and GPUs.☆16Oct 24, 2026Updated 2 weeks ago
- Token-budgeted codebase discovery for agent shells and Pi: cross-language maps, focused navigation, and impact analysis.☆16Updated this week
- ☆13Oct 25, 2025Updated last year
- Local Topsha 🐧 AI Agent for simple PC tasks - focused on local LLM (GPT-OSS, Qwen, GLM)☆150May 11, 2026Updated 5 months ago
- Фреймворк для бенчмаркинга AI-harness. Запускает агентов на наборах задач, оценивает качество ответов и отображает результаты в Web UI с …☆30Jun 30, 2026Updated 4 months ago
- Qwen3.6/3.8-27B on one RTX 5090: 576K pooled context across 12 sessions at FP8-level quality from 5.75 bpw. EXL3 trellis weights, 4-bit t…☆29Oct 23, 2026Updated 2 weeks ago
- ☆17Dec 30, 2025Updated 10 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.
- Your Zero-Code AI File Expert☆16Feb 27, 2026Updated 8 months ago
- PCIe P2P on consumer RTX 5090 via one GSP firmware registry key — no driver patches.☆24Apr 17, 2026Updated 6 months ago
- roblox cookie exstention stealer 0/64 detection☆12Sep 9, 2024Updated 2 years ago
- Unofficial implementation of paper : Exploring the Space of Key-Value-Query Models with Intention☆12May 24, 2023Updated 3 years ago
- ☆24Nov 4, 2025Updated last year
- Pretty fast, pretty simple K3S clusters for Raspberry Pi☆14Jul 25, 2024Updated 2 years ago
- My attempt at absolutely maxxing out my gaming PC for AI inference via the intel Arc B70 platform☆16Aug 26, 2026Updated 2 months ago