Strata fork: Qwen3.8-Flash-Next 125B MoE in NVFP4 on one RTX 20-50 card (12 GB+) and 64 GB of RAM or more. Setup installs our GPTQ quants (huihui abliterated, OrcaRouter) from Hugging Face. CPU experts on AVX-512 or AVX2 (+AVX-VNNI), all experts in RAM from 92 GB, a low-RAM mode below, vision, W4A8 prompts. Windows / CUDA 13.
☆160Oct 15, 2026Updated this week
Alternatives and similar repositories for strata-nvfp4
Users that are interested in strata-nvfp4 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- CUDA Blackwell performance fork of antirez/ds4 (DeepSeek-V4-Flash): ~4x prefill, ~1.5x decode, continuous batching, weight server, DSpark☆77Sep 4, 2026Updated last month
- Portable optimized ROCm and Qwen3.8-27B setup for AMD Strix Halo☆83Sep 16, 2026Updated last month
- Local inference engine for Qwen3.8-Flash-Next on NVIDIA Blackwell☆68Updated this week
- Durable local inference for Oh My Pi: NInfer + Qwen3.8 27B on one RTX 3090/4090/5090, with restart-resumable OpenAI Responses state.☆45Updated this week
- Community-tested recipes, diagnostics, and benchmarks for CMP 170HX AI workloads☆83Oct 10, 2026Updated last week
- 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.
- An introduction to the ideas, implications and technical design principles of the decentralized web. Viewable at☆11Jan 10, 2020Updated 6 years ago
- Self-improving Codex loop: DeepSeek runs the task, Luna grades it, Sol rewrites the prompt until it is done☆47Sep 16, 2026Updated last month
- A GPU-based cross-platform UI library☆13Dec 7, 2019Updated 6 years ago
- ENGRAFT: write facts into an LLM's n-gram (Engram) memory table as a removable overlay: 100 facts in a 9 MB file, no weights touched, ver…☆56Sep 30, 2026Updated 2 weeks ago
- vLLM + Qwen3.6-27B (BF16) OpenAI-compatible inference server on AMD Strix Halo (Ryzen AI Max+ 395, gfx1151). Vision input, 256K context, …☆18Apr 26, 2026Updated 5 months ago
- ☆41Aug 16, 2026Updated 2 months ago
- CPU Software Rasterizer project made with SDL☆12Apr 26, 2024Updated 2 years ago
- Container toolbox that runs llama.cpp with AMD ROCm and NVIDIA CUDA in one build, for inference on two GPUs☆20Updated this week
- Qwen3.8-27B-NVFP4 on a Single RTX 5090 (vLLM)☆96Aug 16, 2026Updated 2 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Performance-tuned llama.cpp for AMD Strix Halo (gfx1151): FA + MoE-prefill fixes with a bundled current Mesa driver. Vulkan and HIP; port…☆216Oct 9, 2026Updated last week
- ☆13Dec 19, 2016Updated 9 years ago
- nano 3d is a small modern software rasterizer☆13Mar 11, 2018Updated 8 years ago
- Fastest measured Qwen3.8-27B config for DGX Spark (GB10): SGLang + NVFP4 + DFlash2, 71.4 tok/s greedy median, 1M context, deterministic b…☆228Updated this week
- ☆17Dec 10, 2018Updated 7 years ago
- High-performance single-GPU inference for selected model checkpoints and GPUs.☆237Sep 14, 2026Updated last month
- Fix broken json using Python☆25Jun 28, 2026Updated 3 months ago
- Absolutely not my submissions for a Linux kernel challenge☆20Jul 17, 2018Updated 8 years ago
- Async task queue + persistent memory for AI agents. Never lose context between sessions. Works with Claude Code, Remote Control, and Clau…☆26Apr 13, 2026Updated 6 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.
- Simple Ocean implementation using Ogre 2.1 and the Terra tutorial as base, with a nice baked animated texture, for more info see http://w…☆19Dec 28, 2019Updated 6 years ago
- Tweaker for Windows 11☆18Aug 18, 2026Updated last month
- ☆68Aug 24, 2026Updated last month
- The $0 AI Empire Playbook — 180 scheduled jobs, 43 free LLM lanes, and the failure classes that almost killed it. Free tiers only.☆101Sep 22, 2026Updated 3 weeks ago
- Speed of light ray-tracer☆23Sep 2, 2017Updated 9 years ago
- Patcher for Pinball Arcade that enables Oculus Rift support (Windows only)☆19Oct 15, 2014Updated 12 years ago
- EvoX Genesis is an autonomous system for long-horizon software evolution that recursively builds, continues, and transforms complex softw…☆72Updated this week
- This repo contains the source code for https://pest.rs☆13Updated this week
- An AI-powered intelligent disk cleanup assistant; 一款 AI 驱动的智能磁盘清理助手。☆334Sep 10, 2026Updated last month
- 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.
- Qwen 3.8 27B ROCmFP4 on AMD Strix Halo (Ryzen AI Max+ 395). Up to 36 tok/s via MTP Speculation, TurboQuant & Mesa RADV Wave64.☆257Sep 7, 2026Updated last month
- SamuraiThirdPersonTemplateThreeJS☆105Aug 17, 2026Updated 2 months ago
- Unreal Engine 4 Plugin MultiPacker Source Code Repository , the plugin its a packer for textures and materials (baked) by atlas binpackin…☆20Oct 23, 2019Updated 6 years ago
- Step-by-step guide to set up Sparky, the HackRF radio assistant☆71Aug 9, 2026Updated 2 months ago
- Single-request LLM serving recipes, patches, and benchmarks for modified RTX 2080 Ti 22GB / SM75 systems☆92Jun 10, 2026Updated 4 months ago
- CMP 170HX technical wiki: silicon, firmware, the community unlock, procedures and open problems. 55 pages.☆71Aug 22, 2026Updated last month
- A 3D rasterizer/path tracing engine☆21Feb 7, 2026Updated 8 months ago