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 tok/s at 16 users. TensorFold + MiaAI-Lab recipe + 29 patches.
☆16Nov 15, 2026Updated this week
Alternatives and similar repositories for pico-dgx-qwen38
Users that are interested in pico-dgx-qwen38 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 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
- DeepSeek V4.1 Flash on 4x DGX Spark: 90/144 tok/s chat/code single-user, 376 tok/s at 16 distinct users, 1M context, images. Fork of blae…☆151Updated this week
- GLM-5.3-Flash on DGX Sparks (ver 1104) with TensorFold☆145Nov 11, 2026Updated last week
- DeepSeek-V4.1-Flash on 4x DGX Spark (GB10): exact 4-node TensorFold (Zig) recipe, vision, 1M context☆14Updated this week
- Did your change make your LLM server faster? Measure it: faster, slower, or too close to call. Linux and Apple Silicon.☆16Updated this week
- 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.
- 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…☆11Oct 14, 2026Updated last month
- More memory for CUDA on an NVIDIA GB10 (DGX Spark, ASUS Ascent GX10): lend the unused display carveout to vLLM, SGLang and TensorFold as …☆48Updated this week
- Hardware build recipes☆24Nov 14, 2026Updated last week
- 8s of H3 video in 2m54s warm delivery on two DGX Sparks. Scene-specific LTX refinement, original-voice restoration, measured sync, clips …☆24Sep 12, 2026Updated 2 months ago
- Inference engine with adaptive expert loading. DeepSeek V4.1 Flash, GLM 5.3 Full and GLM 5.3 Flash, Inkling 2 small.☆55Updated this week
- 2.5D game assets as code: props, scenery, rigged characters, effects, item icons and HUD in TypeScript, exported as sprite sheets for gam…☆28Nov 13, 2026Updated last week
- GLM-5.3-Flash (abliterated EXL3) on 2x NVIDIA DGX Spark with the TensorFold engine: 1.8x faster decode than vLLM, 4x256k concurrent threa…☆126Oct 30, 2026Updated 3 weeks ago
- DeepSeek v4.1 Flash EXL3 2.9 bpw for 2x DGX Sparks☆284Sep 19, 2026Updated 2 months ago
- Qwen3.8 Flash Next on one DGX Spark (TensorFold)☆446Updated this week
- 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.
- Reproducible kit to deploy DeepSeek-V4-Flash-DSpark on a 2× NVIDIA DGX Spark (GB10) cluster: vLLM TP=2 over QSFP 200GbE, NVFP4 KV, DSpark…☆13Aug 24, 2026Updated 2 months ago
- A local-first AI companion that keeps watching while nobody is talking, so it can tell you what you were doing five minutes ago. Runs ent…☆10Jul 29, 2026Updated 3 months ago
- Ornith-1.5-122B (EXL3-EAQ) on one DGX Spark with TensorFold☆23Oct 21, 2026Updated last month
- Qwen3.8-Flash-Next-NVFP4-vLLM-Dual-DGX-Spark☆418Sep 29, 2026Updated last month
- Concurrency Patch to enable on DSpark - DeepSeek V4 Flash/Pro C=16 can be modified for more☆12Jun 29, 2026Updated 4 months ago
- Verified Qwen3.8 Flash-Next GGUF recipe for one NVIDIA DGX Spark or ASUS Ascent GX10☆60Nov 11, 2026Updated last week
- Optimized two-node DGX Spark deployment recipe for DeepSeek V4 Flash with vLLM, DSpark, and NVFP4 KV cache☆11Aug 12, 2026Updated 3 months ago
- GLM-5.3 EXL3 on DGX Sparks with TensorFold☆86Oct 4, 2026Updated last month
- VS Code extension: watch Hermes agents work as pixel characters in a virtual office☆14Aug 10, 2026Updated 3 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Break Linux, not your Mac. A tiny macOS menu bar app for disposable Ubuntu machines you can SSH into, built on Apple's container.☆17Updated this week
- DeepSeek-V4.1-Flash on 2x NVIDIA DGX Spark with the TensorFold engine: 1.8-1.9x code, 2.5x multi-stream, 1.7-1.95x prefill vs the vLLM ki…☆151Updated this week
- Rebuild Star Wars Battlefront II (2017) maps in the browser from your own installed copy: extraction, decoding and a three.js runtime. No…☆32Oct 16, 2026Updated last month
- TandemEngine: local inference that drafts and verifies its own tokens, behind an OpenAI-compatible API.☆82Updated this week
- Uncensored DeepSeek-V4.1-Flash-1017 on 2x DGX Spark: refusals 94 to 6, same answers as DeepSeek's API, 2,008 tok/s prefill at 128K, 113 t…☆63Oct 27, 2026Updated 3 weeks ago
- Reproducible vLLM recipe: nvidia/Qwen3.8-Flash-Next-NVFP4 on one NVIDIA DGX Spark (GB10) — pinned nightly, patches with provenance, build…☆35Oct 28, 2026Updated 3 weeks ago
- Inkling-Small-NVFP4 on 2x NVIDIA DGX Spark (GB10/SM121): pinned vLLM config, MTP speculative decoding, 60 tok/s peak c1. One-command brin…☆14Aug 22, 2026Updated 3 months ago
- An Overwatch match detection app with SMS notifications.☆10Jan 20, 2022Updated 4 years ago
- Self-hosted live telemetry, alerts and benchmarks for NVIDIA DGX Spark (GB10) clusters☆12Updated this week
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Local workload scheduler for autonomous agents sharing an Apple Silicon Mac.☆13Nov 4, 2026Updated 2 weeks ago
- Fabreeko's Doron Velta☆22Sep 1, 2024Updated 2 years ago
- Qwen3.8-Flash-Next on two DGX Sparks with TensorFold☆63Oct 26, 2026Updated 3 weeks ago
- sparkDash ⚡ — Multi-DGX Spark Monitoring Dashboard☆912Updated this week
- MiniMax-H3 on single DGX Spark: keys Sol-Engine ports + Heretic TE + Spectrum/Sage speed + 0.5MP upscaler finish. Formal bench included.☆51Aug 23, 2026Updated 2 months ago
- A simple tool to ensure compatibility between microservices☆16Jul 3, 2019Updated 7 years ago
- The digital cork board for filmmakers. Index cards, acts, arcs, and episodes — a local-first planning wall for features, TV, shorts, musi…☆24Jul 28, 2026Updated 3 months ago
Are these results useful?