Working recipe: MiniMax-M3 NVFP4 at tensor-parallel 3 across 3x DGX Spark (GB10/sm_121) with clean tool-calling. Includes the head-node OOM fixes and multi-node Ray/NCCL setup. Open for tinkering + fixes.
☆16Jul 13, 2026Updated 4 months ago
Alternatives and similar repositories for Minimax-M3-NVFP-3x-DGX-Sparks-TP-3
Users that are interested in Minimax-M3-NVFP-3x-DGX-Sparks-TP-3 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- MiniMax-M3 (428B, no pruning) at 36 tok/s on 2× NVIDIA DGX Spark — W4A16 GPTQ + NVFP4 KV + EAGLE-3 speculative decoding on vLLM. Three se…☆45Jul 13, 2026Updated 4 months ago
- Concurrency Patch to enable on DSpark - DeepSeek V4 Flash/Pro C=16 can be modified for more☆12Jun 29, 2026Updated 4 months ago
- Optimized two-node DGX Spark deployment recipe for DeepSeek V4 Flash with vLLM, DSpark, and NVFP4 KV cache☆11Aug 12, 2026Updated 3 months ago
- Repository template for projects or products based on IQGeo Platform☆14Nov 3, 2026Updated last week
- A very-low-resource API-compatible replacement for Ray☆13Nov 1, 2026Updated 2 weeks 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.
- Agentic test batteries for local models via Hermes Agent - scripted tools + real Hermes CLI sessions☆15Aug 14, 2026Updated 3 months ago
- ☆17Nov 7, 2026Updated last week
- 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 2 months ago
- RDMA networking + MPI for consumer GPU clusters — no managed switch required☆32Mar 18, 2026Updated 7 months ago
- 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
- The dailies room for AI filmmaking — organize every generated take by shot, gate them with local AI quality checks (character drift, flic…☆30Jul 25, 2026Updated 3 months ago
- GLM-5.3-Flash (320B MoE) at TP4 across four DGX Sparks, same day as the model drop: 36 tok/s, 1.26M-token FP8 KV pool, 262K context, MTP …☆57Oct 10, 2026Updated last month
- Run on TWO-DGX-Spark - vLLm-0.24.0 dual cache optimized DSV4F+DSpark+NVFP4 KV (Concurrency 12 with 1.5M context/3M KV token Pool) >0.58-0…☆21Aug 17, 2026Updated 2 months ago
- Open Source Desktop App for Local-first pre-production canvas for AI video planning, prompts, assets, and handoff packages.uggested Donat…☆39Jul 20, 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.
- Minimal read-only OS image for GB10 (DGX Spark / ASUS GX10) boxes☆99Updated this week
- DeepSeek-V4-Flash-DSpark optimized vLLM 0.26.0 SM121 dual-GB10 evidence (NVFP4 KV, B12X, DSpark K6)☆31Aug 3, 2026Updated 3 months ago
- SparkHome: a tvOS-style home screen and voice assistant for the NVIDIA DGX Spark. Plugins for controllers, tiles and connectors; MCP for …☆39Nov 2, 2026Updated 2 weeks ago
- llama-server start/stop scripts for Qwen3.6-35B-A3B UD-Q8_K_XL GGUF on DGX Spark☆26Jul 6, 2026Updated 4 months ago
- Flipper Zero signals and libuhd C++ demod examples☆14Jul 6, 2026Updated 4 months ago
- MiniMax-H3 33B audio+video DiT accelerated 1.54x on a single NVIDIA DGX Spark (GB10, sm_121): NVIDIA Sol-Engine FirstBlockCache + batched…☆34Aug 17, 2026Updated 2 months ago
- Proof of Concept exploit for Kubernetes CVE-2020-8559☆20Jul 22, 2020Updated 6 years ago
- Archived: b12x development has moved to FlashInfer. See README for migration and PR-porting guidance.☆269Oct 6, 2026Updated last month
- keys-DGX-Sparkticus Utimate Power Pack Unleashed (Dual DGX-Sparks Needed)☆44Aug 23, 2026Updated 2 months ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- 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
- DeepSeek V4 Flash @ 1M token context on 2x NVIDIA DGX Spark — production-tested recipe (45 tok/s decode, real 800K prompts served)☆37Jul 13, 2026Updated 4 months ago
- ☆19Sep 9, 2026Updated 2 months ago
- Eight-system DGX Spark engineering: fabric repair, NCCL tuning, rack recabling, custom 3D-printed PSU supports, and thermal validation.☆11Aug 3, 2026Updated 3 months ago
- Qwen3.6 27B × DFlash — 30-35 tok/s on NVIDIA DGX Spark (GB10) - LLama.Cpp☆17May 2, 2026Updated 6 months ago
- Model-agnostic LLM benchmarking + tuning in one command. A model is a 15-key profile file. Built in production on a 4x NVIDIA DGX Spark c…☆10Sep 16, 2026Updated last month
- Temperature-driven fan control for NVIDIA DGX Spark: full speed at ≥80 °C, back to EC auto at ≤70 °C. A bash script + systemd service bui…☆12Oct 13, 2026Updated last month
- DeepSeek-V4.1-Flash on 4x DGX Spark (GB10): exact 4-node TensorFold (Zig) recipe, vision, 1M context☆14Nov 4, 2026Updated last 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.
- 🚗 LIMCARS Local Inference Monitor · Cost Analyzer · Recipe Server☆13Updated this week
- A few demos on how the new portal API can be used with React.☆14Apr 19, 2018Updated 8 years ago
- ☆11Nov 7, 2026Updated last week
- MiniMax-M3 (MXFP4, MSA) serving on SM120 (RTX PRO 6000 Blackwell) — patched vLLM image + launch recipe, 192K context☆23Jun 15, 2026Updated 5 months ago
- Agnost GitOps Helm charts☆13Dec 9, 2025Updated 11 months ago
- AEON vLLM Ultimate — vLLM 0.27.1 built from source for DGX Spark / Blackwell (sm_121a/GB10). DSpark quantized Markov heads, DFlash SWA on…☆149Updated this week
- Apollo Engine reporter that sends Absinthe traces built by https://github.com/sikanhe/apollo-tracing-elixir to Apollo engine directly wi…☆15Dec 15, 2022Updated 3 years ago
Are these results useful?