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 3 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 3 months ago
- Concurrency Patch to enable on DSpark - DeepSeek V4 Flash/Pro C=16 can be modified for more☆12Jun 29, 2026Updated 3 months ago
- MiniMax-H3 on single DGX Spark: keys Sol-Engine ports + Heretic TE + Spectrum/Sage speed + 0.5MP upscaler finish. Formal bench included.☆49Aug 23, 2026Updated 2 months ago
- Agentic test batteries for local models via Hermes Agent - scripted tools + real Hermes CLI sessions☆15Aug 14, 2026Updated 2 months ago
- NVFP4 Gemma-4 26B-A4B MoE for DGX Spark — optimal recipe: DFlash n=10 (flex) on AEON vLLM Ultimate. 144 tok/s single / 1,724 peak (Coding…☆46Oct 6, 2026Updated 2 weeks ago
- 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.
- Repository template for projects or products based on IQGeo Platform☆14Sep 3, 2026Updated last month
- GLM-5.3-Flash NVFP4 on 4x NVIDIA DGX Spark: vLLM TP4, DFlash2 adaptive draft, measured FP8 vs NVFP4 vs EXL3 vs SGLang☆39Sep 29, 2026Updated 3 weeks ago
- 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
- ☆19Sep 9, 2026Updated last month
- MiniMax-H3 33B audio+video DiT accelerated 1.54x on a single NVIDIA DGX Spark (GB10, sm_121): NVIDIA Sol-Engine FirstBlockCache + batched…☆35Aug 17, 2026Updated 2 months ago
- Run DeepSeek-V4-Flash at full 1M context AND two MiniMax H3 video instances on the same two DGX Sparks. Benchmarked C1-C6.☆35Aug 7, 2026Updated 2 months ago
- MiniMax-M3 (MXFP4, MSA) serving on SM120 (RTX PRO 6000 Blackwell) — patched vLLM image + launch recipe, 192K context☆22Jun 15, 2026Updated 4 months ago
- DeepSeek-V4-Flash-DSpark optimized vLLM 0.26.0 SM121 dual-GB10 evidence (NVFP4 KV, B12X, DSpark K6)☆31Aug 3, 2026Updated 2 months ago
- Give any blind LLM eyes — on any machine — in one shot. Tiny local VLM (Qwen3.5-0.8B) as an OpenAI-compatible vision service. Mac (MLX) /…☆28Jul 7, 2026Updated 3 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- keys-DGX-Sparkticus Utimate Power Pack Unleashed (Dual DGX-Sparks Needed)☆43Aug 23, 2026Updated 2 months ago
- llama-server start/stop scripts for Qwen3.6-35B-A3B UD-Q8_K_XL GGUF on DGX Spark☆26Jul 6, 2026Updated 3 months ago
- Augmented Reality integration in a Ionic 2 application☆10Feb 19, 2017Updated 9 years ago
- The digital cork board for filmmakers. Index cards, acts, arcs, and episodes — a local-first planning wall for features, TV, shorts, musi…☆18Jul 28, 2026Updated 2 months ago
- DeepSeek-V4.1-Flash-1017 on NVIDIA DGX Sparks with TensorFold + EXL3: TP4 (4 Sparks, 93.6 tok/s, 1M context) and TP2 (2 Sparks, 73 tok/s)…☆146Updated this week
- Open-source Cantonese (HK) TTS — CPU-first ONNX inference SDK☆16Aug 1, 2026Updated 2 months ago
- Headless / multi-user serving-mode for the DGX Spark: free unified memory for vLLM by paring back the desktop. Companion to qwen3.5-122B-…☆20Jun 29, 2026Updated 3 months ago
- MiMo-V2.5 Omni TP=2 on 2x DGX Spark · 1M context · NVFP4 4-bit KV (~1.97M-token KV pool @ 1M, ~30 tok/s) · 69-eval: thinking-OFF 97.8 bea…☆39Jul 13, 2026Updated 3 months ago
- ☆10Mar 18, 2024Updated 2 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- GLM-5.2 NVFP4+AQLM on 3× DGX Spark — 380k context MTP serve stack☆72Aug 2, 2026Updated 2 months ago
- DGX Spark (GB10/sm_121) port: DeepSeek-V4-Flash 159B on one Spark, GLM-5.2 753B across two. Prepacked 2-bit planes + unified-memory fixes…☆19Jul 20, 2026Updated 3 months ago
- ROCmfp4☆24May 25, 2026Updated 5 months ago
- A community-owned map of LLM inference engine configurations — benchmarks, evals and coverage gaps, hosted on GitHub Pages. The repo is t…☆16Updated this week
- Agent-ready two-node DGX Spark recipe for DeepSeek V4 Flash plus an optional Qwen Vision sidecar, with generic OpenAI-compatible, Hermes,…☆24Aug 10, 2026Updated 2 months ago
- A few demos on how the new portal API can be used with React.☆14Apr 19, 2018Updated 8 years ago
- Agnost GitOps Helm charts☆13Dec 9, 2025Updated 10 months ago
- Distillation pipeline from pretrained Transformers to customized FLA models☆13Aug 4, 2025Updated last year
- Three-DGX-Spark TP3 serving recipe for GLM-5.3 Flash☆19Oct 5, 2026Updated 2 weeks ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- NVIDIA GDX Spark Dashboard☆14Feb 9, 2026Updated 8 months ago
- ☆20Aug 10, 2026Updated 2 months ago
- The prompt studio for AI filmmaking — plan shots, direct coverage, keep continuity, and compile production-ready prompts for any image, v…☆70Aug 9, 2026Updated 2 months ago
- Honeycomb Lab — hex map + OpenAI gateway control plane for a home AI fleet☆17Updated this week
- Drag-n-drop entites using mouse cursor.☆13Dec 4, 2022Updated 3 years ago
- Index and search a bunch tweets with Meteor and Elasticsearch☆13Jun 29, 2015Updated 11 years ago
- 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