GLM-5.3-Flash EXL3 K2 2.33bpw on ONE DGX Spark: native MTP (layer 45, 288 experts), CUDA graphs on, full 262,144 ctx. Measured ~19 tok/s sampled decode, receipts included. Fork of the 2x kit.
☆10Sep 19, 2026Updated last month
Alternatives and similar repositories for GLM-5.3-Flash-EXL3-1x-DGX-Spark
Users that are interested in GLM-5.3-Flash-EXL3-1x-DGX-Spark are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- DeepSeek-V4.1-Flash EXL3 on 2x DGX Spark (GB10) with the TensorFold engine, TP=2☆13Oct 10, 2026Updated last month
- ☆55Sep 13, 2026Updated last month
- Based on OMSCS. 🎓 Collaborative open source notes for graduate computer science courses.☆13Apr 14, 2024Updated 2 years ago
- DeepSeek-V4.1-Flash on a single DGX Spark (GB10): resident hot experts + NVMe streaming, DSpark, OpenAI API. Work in progress.☆128Sep 16, 2026Updated last month
- Serve Qwen3.8-Flash-Next (turboderp ExLlamaV3 pack) on one NVIDIA DGX Spark with exllamav3☆65Oct 14, 2026Updated 3 weeks ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Cap the GPU clock on NVIDIA DGX Sparks across all your machines, persistently☆105Oct 14, 2026Updated 3 weeks ago
- Qwen3.8-27B on one DGX Spark GB10: DFlash 2 for 65 tok/s C1 and 120 C4; EAGLE 3/1/4 for ~191 C8, ~330 C16 and ~535 C32; native 262K, pinn…☆13Oct 6, 2026Updated last month
- SparkGLM Atlas engine: Enntity's fork of Mango-kid/atlas (Atlas-Inf/atlas), AGPL-3.0☆11Updated this week
- Qwen3-ASR-FastAPI-Docker: Lightweight FastAPI service containerizing Qwen3-ASR for low-latency multilingual speech, music, and singing re…☆15Jan 31, 2026Updated 9 months ago
- ☆13Aug 27, 2026Updated 2 months ago
- DeepSeek v4 Flash EXL3 on one DGX Spark☆350Aug 24, 2026Updated 2 months ago
- ☆14Jan 29, 2026Updated 9 months ago
- A minimalist YouTube transcript downloader made for the agent era — one click gets any video’s captions into Codex or Muse. No popups, ad…☆12Sep 20, 2026Updated last month
- An OpenAI-compatible API server for Rockchip NPUs (RK3588/RK3576). Run LLMs locally on the edge with hardware acceleration.☆20Mar 20, 2026Updated 7 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- rkllm rust ffi binding☆13Oct 19, 2026Updated 3 weeks ago
- A high performance authentication and access-control gateway for LLM API backends☆17Jun 11, 2026Updated 5 months ago
- MacOS dotfiles☆13Nov 4, 2026Updated last week
- DSV4.1-Flash-1017 SAGE EXL3 (1.62 bpw) on one DGX Spark with vLLM: DSpark MTP, cold-expert ATS alias, tile-K 16 MoE, memory guard, measur…☆42Nov 4, 2026Updated last week
- Serving 4-bit Qwen3.8-27B on a single DGX Spark (GB10): 75 tok/s single-stream, 246 tok/s aggregate at 8-way concurrency. NVFP4 vs MixedI…☆51Sep 29, 2026Updated last month
- Ubuntu 24.04 + NVIDIA stack setup guide for GB10 / DGX Spark systems☆24Nov 1, 2026Updated last week
- Qwen3.8-Flash-Next on ONE DGX Spark (TP=1)☆630Oct 4, 2026Updated last month
- Pinned one-DGX-Spark Docker recipe for DeepSeek V4 Flash with EXL3, SparkInfer, and 262K NVFP4 MLA KV cache☆167Sep 3, 2026Updated 2 months ago
- ☆26Updated this week
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Collection of open-source JavaCard crypto algorithms. Optimized for memory and speed with unified interface☆14Oct 6, 2024Updated 2 years ago
- ☆11Aug 4, 2021Updated 5 years ago
- One native app for every AI coding agent. Rust + GPUI.☆14Updated this week
- GLM-5.3-Flash on DGX Sparks (ver 1104) with TensorFold☆98Updated this week
- A Rust-native LLM serving engine. One binary, no Python runtime.☆22Updated this week
- A manga reader site built in PHP. Utilises a public API and Bootstrap to display content.☆10Jun 25, 2016Updated 10 years ago
- Qwen3.8 Flash Next on one DGX Spark (TensorFold)☆393Oct 30, 2026Updated last week
- Coding stack built completely on local models☆21Aug 22, 2026Updated 2 months ago
- Self-hosted AI pilot for any codebase. Researcher and critic agents plan, execute and verify each change.☆15Sep 16, 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.
- sparkDash ⚡ — Multi-DGX Spark Monitoring Dashboard☆850Updated this week
- ☆11Sep 28, 2025Updated last year
- Multiplayer coding rooms with Claude. Multiple developers, one AI agent, real-time collaboration.☆12May 25, 2026Updated 5 months ago
- ☆16Sep 25, 2026Updated last month
- Idol: a single image to 3D Gaussians. Inference SDK and demo.☆19Updated this week
- SGLang optimizations for NVIDIA Spark (GB10) — SM121 Grace Blackwell☆13Updated this week
- Mix-and-matching React & Svelte 5☆13Aug 9, 2025Updated last year
Are these results useful?