Inkling-Small-NVFP4 on 2x NVIDIA DGX Spark (GB10/SM121): pinned vLLM config, MTP speculative decoding, 60 tok/s peak c1. One-command bring-up.
☆14Aug 22, 2026Updated 2 months ago
Alternatives and similar repositories for Inkling-Small-2-Sparks
Users that are interested in Inkling-Small-2-Sparks are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- An in-app browser pane for DeepSeek Harness — real Chrome over CDP, plus rendered previews of local files, markdown and PDFs.☆16Sep 28, 2026Updated last month
- SparkGLM Atlas engine: Enntity's fork of Mango-kid/atlas (Atlas-Inf/atlas), AGPL-3.0☆12Updated this week
- Scripts to setup a two-node llama.cpp cluster on NVIDIA DGX Spark (GB10) hardware.☆12May 10, 2026Updated 6 months ago
- Local model hosting with 2x DGX Sparks☆12Aug 29, 2026Updated 2 months ago
- Lighting effect for Keyboardio Model 01 that colors keys by function☆10Sep 29, 2022Updated 4 years ago
- 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.
- Tested MiaAI-based DeepSeek V4 Flash speed profile for two ASUS GX10s: pinned patch, settings, and benchmark helper.☆15Sep 5, 2026Updated 2 months ago
- Uncensored Qwen3.8-27B Ultimate - BF16 master + NVFP4-MIXED deploy. QuickStarts for DGX Spark (one Dynamic DFlash lattice seat @ util 0.8…☆21Nov 13, 2026Updated last week
- Native cross-platform desktop client for NaN community and Helmcode enterprise inference☆13Updated this week
- The kernel for the Wink Hub☆11Oct 29, 2014Updated 12 years ago
- 𝒕𝒈(𝒇x) - a tiny Telegram bridge for fx coding agent☆13Nov 9, 2026Updated last week
- Kaleidoscope plugin creating an LED 'LetterGuesser' effect.☆15Oct 21, 2017Updated 9 years ago
- Simple starter CMake project that uses NVBench.☆15May 6, 2025Updated last year
- Qwen3.8-Flash-Next on one DGX Spark, official NVIDIA FP4 weights, exact output: 54 chat / 88 code tok/s, 66.9 on 320 held prompts, 288 to…☆16Updated this week
- Complete single-Spark AI agent stack: Qwen 122B + Hermes + Honcho on one DGX Spark☆18Jun 9, 2026Updated 5 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.
- self-hosted persistent Linux workspaces. open-source alternative to boat.dev☆25Nov 14, 2026Updated last week
- Hyperion Ambient Lighting Python Package☆14Jun 1, 2025Updated last year
- .NET class library for accessing the Security Exchange Commission's EDGAR database.☆12Jun 22, 2025Updated last year
- Plugin for Kaleidoscope that allows you to record and play back macros on-the-fly.☆16Aug 12, 2020Updated 6 years ago
- A generator automatically make canonical tag for hexo.☆16Jan 3, 2018Updated 8 years ago
- ☆17Updated this week
- Excalibur is the AI Coding Agent for Product Engineers☆22Sep 17, 2026Updated 2 months ago
- Serve the official Ling-3.0-flash INT4 on one NVIDIA DGX Spark, 38.7 tok/s, faster than the community GGUF. Recipe, watchdog, benchmarks.☆26Aug 29, 2026Updated 2 months ago
- Qwen3.8-27B ADay777-Ablit · NVFP4 · A4Q · NVFP4-KV (4M+ pool) · MTP-3 — single DGX Spark (GB10/sm121), eugr vLLM 0.27. 1M ctx @ c=4.☆24Aug 17, 2026Updated 3 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.
- Dataset abierto de modelos de HuggingFace: metadatos curados y normalizados, licencias clasificadas, parámetros reales, tumbas de modelos…☆21Updated this week
- A Ruby wrapper for the Wink Hub API.☆18May 14, 2015Updated 11 years ago
- Recipe (profiles + docs) to serve Qwen3.8-Flash-Next on 1 or 2 DGX Sparks with the Zig TensorFold engine + Compute Lanes. Engine: github.…☆17Nov 14, 2026Updated last week
- My girlfriend wants me to stop swearing. Let's ask Whisper for some help.☆17Oct 12, 2022Updated 4 years ago
- Add an agent with one CLI command. Source lands in your repo as real TypeScript — prompts, tools, and runtime you can edit and own.☆17Aug 4, 2026Updated 3 months ago
- DeepSeek-V4-Flash-DSpark abliterated (uncensored) · ~100% refusal bypass · C1 ~57 tok/s · 1M ctx · 2× DGX Spark · HF weights☆59Aug 17, 2026Updated 3 months ago
- NVIDIA Nemotron 3.5 Bolt // TensorFold // DGX Spark☆16Nov 1, 2026Updated 2 weeks ago
- CUDA Blackwell performance fork of antirez/ds4 (DeepSeek-V4-Flash): ~4x prefill, ~1.5x decode, continuous batching, weight server, DSpark☆78Oct 26, 2026Updated 3 weeks ago
- Self-hosted family planner for a wall tablet: shared calendar, chores with streaks, meals, reminders and a printed morning briefing for e…☆26Updated this 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.
- Give DeepSeek V4 Flash eyes. OpenAI-compatible shim + tiny local VLM. Point any harness at one URL and your text-only model accepts image…☆30Aug 9, 2026Updated 3 months ago
- Segundo cerebro local-first: Obsidian como interfaz humana, OpenCode como capa de agentes. Plantilla para clonar.☆18Sep 19, 2026Updated 2 months ago
- Omarchy shell plugin: Proton Mail unread count in the bar, recent-messages dropdown and desktop notifications. No extension, no Bridge. W…☆23Aug 30, 2026Updated 2 months ago
- Local OpenTelemetry viewer for traces, metrics, and logs — single binary, persistent DuckDB storage, browser UI.☆20Updated this week
- Unofficial Mercadona API with nutritional information and price history.☆12Jul 28, 2026Updated 3 months ago
- Command-line PAdES PDF signing in pure Rust — an alternative to AutoFirma☆17Oct 27, 2026Updated 3 weeks ago
- English guide + one-command patcher for the vLLM spin-wait bug that overheats NVIDIA DGX Spark / GB10. Credit: nacyot. CPU cores spin at …☆24Aug 17, 2026Updated 3 months ago
Are these results useful?