Local LLM speed measurements from a 4x RTX 3090 rig, with exact launch commands and per-run provenance.
☆18Aug 15, 2026Updated 2 months ago
Alternatives and similar repositories for 4x3090-llm-benchmarks
Users that are interested in 4x3090-llm-benchmarks 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 Flash Next AWQ INT4 4x3090 v1: 262K, Vision, FP8 QSA KV and CUDA Graphs on 4x RTX 3090☆16Aug 30, 2026Updated last month
- A llama.cpp fork with TurboQuant/TCQ KV cache, fused Qwen MTP speculative decoding, and multi-GPU long-context serving fixes.☆24Aug 19, 2026Updated 2 months ago
- A Systematic Verification and Structured Revision of Humanity’s Last Exam☆16Feb 27, 2026Updated 7 months ago
- A complete solution to self host maps☆12Jan 3, 2026Updated 9 months ago
- ☆33Jul 25, 2026Updated 3 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- kivy+pyinstaller打包生成exe☆14Apr 13, 2017Updated 9 years ago
- NInfer SM80 port for NVIDIA CMP 170HX☆28Aug 22, 2026Updated 2 months ago
- ☆13Dec 23, 2020Updated 5 years ago
- Utilities for the Analysis of Ethereum Smart Contracts☆14Jul 29, 2026Updated 2 months ago
- TPU support for the fastai library☆14Apr 15, 2021Updated 5 years ago
- A voice remote for AI agents: push-to-talk, procedural avatar + live status ring on the M5Stack StopWatch (ESP32-S3 round AMOLED). Hermes…☆17Oct 10, 2026Updated 2 weeks ago
- Reverse Shell x86☆16Jan 6, 2019Updated 7 years ago
- 简谱与五线谱的编辑、识谱与排版：图片 / PDF 本地离线识别（OMR）· 谱面可视化编辑 · 试听 · 读写 123 / JP-Word .jpwabc / 文本谱 / ABC / Muse .jcx / MusicXML · 导出 PDF/PNG/MIDI/PPTX ·…☆65Updated this week
- RTX 6000 96GB/Spark 128GB vLLM Recipe for Qwen 3.8 Flash Next☆22Sep 8, 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.
- 150+ free AI models across 20+ providers. Groq, Cerebras, NVIDIA and more with automatic fallback when rate limits hit.☆21Mar 28, 2026Updated 6 months ago
- Easy local setup for Qwen3.8-27B Abliterated: 256K context and measured 240-300 tokens/s generation on an RTX 5090.☆32Sep 20, 2026Updated last month
- Specific Emitter Identification Handling Modulation Variation with Margin Disparity Discrepancy☆13Aug 11, 2025Updated last year
- optimize your claude code usage saving tokens☆15Jun 8, 2026Updated 4 months ago
- Cortex-compatible model server for Python and TensorFlow☆19Nov 27, 2022Updated 3 years ago
- Experiment with NVIDIA Triton and Whisper☆15Apr 29, 2024Updated 2 years ago
- Basic to Advanced LLM Glossary terms☆17Aug 27, 2024Updated 2 years ago
- HRX, LOOM, Mac, and AMD running top speed kernels with a self optimizing engine.☆33Oct 12, 2026Updated last week
- 🃏 The open benchmark where language models play real Balatro.☆28Jul 9, 2026Updated 3 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.
- The space where humans and AI agents collaborate.☆24Updated this week
- Mirai S (Qwen3.8-27B-S trellis GGUF) on a 12 GB RTX 4070: 262k q8_0 tiered cache, MTP drafting at every depth, harness-proofing, the laye…☆101Updated this week
- Implementation of the Adaptive Resonance Theory (ART) architectures - Fuzzy ART and Fuzzy ARTMAP - for pattern recognition☆11Jan 6, 2019Updated 7 years ago
- The elegant integration of huggingface/nlp and fastai2 and handy transforms using pure huggingface/nlp☆19Oct 6, 2020Updated 6 years ago
- An example of how we can move runtime components to a sub-directory in a .NET Core Standalone app☆11Sep 5, 2018Updated 8 years ago
- l3ms - local large language (l3) models - running and orchestrating models locally☆17Oct 7, 2026Updated 2 weeks ago
- ☆16May 31, 2024Updated 2 years ago
- ☆15Feb 20, 2026Updated 8 months ago
- See the unseen. This program visualizes radioactive traces, turning invisible pathways into vibrant maps.☆15Oct 17, 2026Updated last week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Улучшенный морфологический анализатор для русского языка с DAWG-оптимизацией☆44Nov 8, 2025Updated 11 months ago
- ☆20Mar 13, 2023Updated 3 years ago
- I use nix btw☆20Updated this week
- Blender Low Poly Modelling Skill — AI agent skill (Claude Code) that builds flat-shaded, palette-textured, budgeted low-poly game assets …☆17Aug 29, 2026Updated last month
- [Re-implementation] FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence☆15Jun 29, 2020Updated 6 years ago
- Here's my strange, unique beauty: Medusa.☆19Aug 30, 2026Updated last month
- A .NET package for fitting curves to data using particle swarm optimization☆23Sep 25, 2024Updated 2 years ago