Strata for a PC with two NVIDIA GPUs and 32 GB of RAM: the low-RAM mode on a layer split, both cards working at the same time. 143 tok/s on an RTX 5080 + 4060 Ti.
☆84Oct 6, 2026Updated last month
Alternatives and similar repositories for Strata-DualGPU
Users that are interested in Strata-DualGPU are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆11Oct 18, 2026Updated 3 weeks ago
- Strata-based GLM 5.3 Flash runner☆20Updated this week
- C++/CUDA single-GPU inference engine for Qwen3.8 (incl. Qwen3.8-Flash-Next with offloaded experts) on the RTX 5090; grew from NInfer☆288Updated this week
- Local OpenAI- and ElevenLabs-compatible speech, music, and transcription API for MiniMax H3 in ComfyUI☆20Aug 9, 2026Updated 3 months ago
- Cross-tier CPU/GPU hybrid MoE inference for SGLang (plugin, tracks upstream main)☆71Updated this week
- 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.
- Kindi 0.5: local LLM inference on low-cost NVIDIA GPUs (Kepler to the RTX 50 series and the CMP 170HX), AMD Radeon 780M, 840M and 8060S, …☆153Updated this week
- Xolotl: run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM): ~33 tok/s on agent tasks, ~4…☆508Updated this week
- Strata v0.1.42 tuning for 2x RTX 2080 Ti 22G (Qwen3.8-Flash-Next Swift IQ3_XXS): 60K/128K prefill 2116/2163 tok/s on 48GB RAM☆15Oct 14, 2026Updated 3 weeks ago
- Run GLM-5.3 (744B), GLM-5.3-Flash (321B), DeepSeek-V4.1-Flash (748B) and MiniMax-M3.1-Flash (428B) on your own GPUs - one engine, one das…☆2,794Updated this week
- ☆11Updated this week
- ComfyUI workflow for MiniMax-H3-Turbo☆17Oct 23, 2026Updated 2 weeks ago
- 4-bit AWQ INT4 + NVFP4 quantization toolkit for ByteDance Lance multimodal model (image + video)☆15May 20, 2026Updated 5 months ago
- Self-hosted live telemetry, alerts and benchmarks for NVIDIA DGX Spark (GB10) clusters☆12Updated this week
- DeepSeek-V4.1-Flash on two DGX Sparks: EXL3 routed experts, 262k context, 2M-token KV, vision, tools, MTP, bundled with Pi☆96Oct 3, 2026Updated last month
- 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.
- Agent automation for IP-KVMs: one MCP server, CLI, fleet config, and skills driving GLKVM, PiKVM, and TinyPilot. Open-source alternative …☆24Aug 31, 2026Updated 2 months ago
- ☆35Nov 2, 2026Updated last week
- Store MD5 hash in NTFS Alternate Data Stream☆18Aug 7, 2026Updated 3 months ago
- Local inference engine for Qwen3.8-Flash-Next on NVIDIA Blackwell☆915Updated this week
- ☆27Oct 20, 2026Updated 3 weeks ago
- A fast, polished, local Web UI for llama-server, vLLM, and OpenAI-compatible APIs - with charts, diagrams, and MCP tools.☆32Oct 26, 2026Updated 2 weeks ago
- Run Qwen3.8-Flash-Next (main agent) and MiniCPM-V 4.7 (subagents) EXL3 together on one DGX Spark at full 262K context, with a tested Herm…☆10Oct 14, 2026Updated 3 weeks ago
- LLM inference in C/C++☆29Updated this week
- Comfy ui for LLMs using ollama as a backend☆10Jul 15, 2024Updated 2 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.
- vLLM for NVIDIA CMP 170HX (Ampere sm_80): fast, repeatable model serving on one card or several☆28Nov 2, 2026Updated last week
- A Rust inference engine currently targeting AMD R9700 GPU's. buymeacoffee.com/bkuyper☆64Updated this week
- Model Compression Toolbox for Large Language Models and Diffusion Models☆16Aug 19, 2026Updated 2 months ago
- An inference engine for one NVIDIA RTX card, built for a coding agent and its subagents, and a companion that listens, reads and draws: Q…☆63Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆18Sep 11, 2026Updated 2 months ago
- Hyper optimised Qwen3.8-27B inference on one RTX 3090: ReplaySSM, MTP3, reasoning effort, C1-C8 batching, and native Windows and Linux bu…☆509Oct 31, 2026Updated last week
- PolarQuant: Fused KV cache decode kernel that ties cuBLAS on B200 with 4.1x compression☆15Mar 26, 2026Updated 7 months ago
- A Codex skill for clean Chinese-first academic diagrams in any aspect ratio☆14Aug 18, 2026Updated 2 months ago
- ☆124Updated this week
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Natural-language constraints for JEPA world-model planning, judged by a decision model instead of an LLM.☆15Sep 24, 2026Updated last month
- Step-by-step guide to cross-flash the AMD Radeon Pro V620 to a Radeon Pro W6800 for display output, home-lab compatibility, and fan contr…☆16Sep 16, 2026Updated last month
- Dados dos preços e taxas do títulos do tesourodireto.com.br☆14Updated this week
- One-menu RTX 5090 setup for non-Swift Huihui Qwen3.8-27B NVFP4 with Cinference, MTP-10 and K8V4.☆34Sep 22, 2026Updated last month
- A small Node.js script that polls a website and sends a notification when there's a change. Inspired by my attempts to get a close hotel …☆13Nov 10, 2022Updated 4 years ago
- Qwen3.8-27B on One RTX 3090: 14 hours of measurements. Vision crash fix, VRAM math, MTP tuning, quantisation comparison, and 9 pieces of …☆13Aug 17, 2026Updated 2 months ago
- Local VS Code search across Claude Code, Codex, and OpenCode chats with Laya reranking☆69Sep 25, 2026Updated last month
Are these results useful?