DeepSeek-V4.1-Flash-1017 (552B MoE + 196B Engram) on 2x RTX 3090 + 128 GB RAM. Rust + CUDA, T16 quantization. 40+ tok/s measured with expert deferral + FP8 projections.
☆106Nov 4, 2026Updated 2 weeks ago
Alternatives and similar repositories for dsx
Users that are interested in dsx are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Fast open-source (MIT) LLM inference engine in C++/CUDA for RTX 3090-class GPUs: Qwen3.8-Flash-Next (~1,000 tok/s with 8 agents on 3x RTX…☆71Updated 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…☆535Updated this week
- Qwen3.8-Flash-Next at 262K context on an RTX 5090 + RTX 4070 Ti SUPER with 32 GB RAM: Strata patches (prefill on the big card, conversati…☆38Nov 11, 2026Updated last week
- GLM-5.3-Flash EXL3 on one 24 GB RTX 3090 + DDR4: elastic GPU expert cache, zero-copy experts, AVX2 CPU tier, OpenAI API☆352Oct 18, 2026Updated last month
- Qwen3.8-Flash-Next on 2× RTX 3090: with 128 GB RAM up to 4,191 tok/s prefill · 111.5 tok/s decode (131K prompt), full 256K window at 2,86…☆145Oct 15, 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.
- 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…☆3,018Updated this week
- An LDAP to Neo4J loader and analyzer tool☆10May 21, 2019Updated 7 years ago
- llama.cpp fork for significantly improved performance on Ampere generation Nvidia cards (especially RTX 3090 / 3090 Ti): example: 110+ to…☆398Updated this week
- LLM serving engines that SkyDiscover builds on the fly for specific AI models and hardware: Qwen3.6-35B-A3B, Qwen3.8-Flash-Next and Flint…☆44Nov 4, 2026Updated 2 weeks ago
- Tensor parallelism is all you need. Run LLMs on an AI cluster at home using any device. Distribute the workload, divide RAM usage, and in…☆18Nov 11, 2024Updated 2 years ago
- Autonomous, local-first multi-agent AutoML platform. Zero cloud costs, zero API keys, 100% private. Benchmarks 7 algorithms, tunes hyperp…☆23Oct 26, 2026Updated 3 weeks ago
- Fermion Research fork of llama.cpp: FV5/FV5B five-value ternary types for Neutrino GGUF packs (CPU + CUDA)☆14Sep 29, 2026Updated last month
- Raw speed benchmark traces: Qwen3.8-27B on 4x RTX 3090. llama.cpp GGUF sweeps + 288-point vLLM vs SGLang, NVFP4 vs FP8 matrix.☆14Sep 28, 2026Updated last month
- Fastest validated sglang recipe for Qwen3.8-27B (AWQ-INT4 + DSpark) on RTX 3090s — 1×/2×/4× GPU presets, image+video, full benchmarks☆66Oct 17, 2026Updated last month
- 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.
- GPU peer-to-peer over dynamic BAR1 for GeForce cards: patched NVIDIA open kernel modules.☆26Nov 6, 2026Updated last week
- Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when …☆2,751Nov 10, 2026Updated last week
- ☆41Aug 16, 2026Updated 3 months ago
- Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, sglang, llama.cpp and other custom engines) and m…☆2,505Updated this week
- ☆14Oct 14, 2026Updated last month
- Unlock P2P comms between consumer NVIDIA GPUs☆735Oct 26, 2026Updated 3 weeks ago
- PlayTrain: LLM-generated JavaScript game environments for RL☆12Oct 8, 2026Updated last month
- Benchmark your local LLMs with real evaluation suites. Not vibes - actual scores.☆41Updated this week
- Qwen3.8-Flash-Next at full 262k context on 8 GB RAM and 16 GB VRAM—20 tok/s generation and 1,600 tok/s prefill.☆67Oct 26, 2026Updated 3 weeks ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Community registry of LLM serving-path traps that produce confidently wrong measurements: templates, tool parsers, reasoning fields, quan…☆178Updated this week
- Experimental llama.cpp fork for inference research and development☆910Updated this week
- CPU-GPU hybrid inference for DeepSeek-V4 on NVIDIA SM80+ (A100/RTX 4090 etc.), forked from yhfgyyf/vllm-deepseek-v4-sm89.☆61Sep 16, 2026Updated 2 months ago
- Bonsai 2 27B: 262k context (trained max) on 12 GB, 54 to 97 tok/s decode, 2x prefill, q8_0 KV recipe, grammar tool calls 9/9. Same ternar…☆100Updated this week
- 🌐 Ultimate Standalone Terminal Browser & Web Scraper MCP - Browse any website, extract content & links directly in terminal with zero fi…☆12Jul 13, 2025Updated last year
- Lua for Plan9 space☆10Jul 5, 2025Updated last year
- Implement FlashAttention v2 with minimal code to learn.☆19Jun 12, 2024Updated 2 years ago
- Verified multi-source distribution for local LLM weights☆18Nov 4, 2026Updated 2 weeks ago
- A patching tool to remove the numpy<2 constraint from official mediapipe wheels.☆11Jun 23, 2026Updated 4 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.
- ☆11Jul 14, 2020Updated 6 years ago
- Mirror of https://code.9front.org/hg/purgatorio ;; syncs on the hour CST☆10Jun 3, 2021Updated 5 years ago
- unofficial version of eratoho TWKR☆25Aug 19, 2025Updated last year
- Repo for arxiv paper "A Systematic Study of Code Obfuscation Against LLM-based Vulnerability Detection".☆15Dec 18, 2025Updated 11 months ago
- clone from http://qt.gitorious.org/qt-labs/wolfenqt☆13Dec 10, 2012Updated 13 years ago
- Pure Lua JSON schema (draft 4) validator for Lua and OpenResty☆14Feb 13, 2026Updated 9 months ago
- Specialized fork for (relatively) fast single-GPU inference (in CUDA) using large MoE models that don't fit fully into VRAM☆17May 6, 2026Updated 6 months ago
Are these results useful?