MiniMax M2.7 NVFP4 dual-GB10 Blackwell benchmark: vLLM FlashInfer-CUTLASS, public data, HTML canvas report, and Docker runtime.
☆12May 24, 2026Updated 5 months ago
Alternatives and similar repositories for minimax-m27-nvfp4-gb10-benchmark
Users that are interested in minimax-m27-nvfp4-gb10-benchmark are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 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 2 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 2 weeks ago
- Hermes Agent benchmark v0.1 — evaluate local models on the actual tool-calling patterns Hermes users hit. Reproducible, trace-capturing, …☆17Jun 24, 2026Updated 4 months ago
- Tested MiaAI-based DeepSeek V4 Flash speed profile for two ASUS GX10s: pinned patch, settings, and benchmark helper.☆15Sep 5, 2026Updated last month
- ☆19Sep 9, 2026Updated last month
- 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.
- MiniMax-M3 (MXFP4, MSA) serving on SM120 (RTX PRO 6000 Blackwell) — patched vLLM image + launch recipe, 192K context☆22Jun 15, 2026Updated 4 months ago
- Working recipe to serve DeepSeek-V4-Flash across two NVIDIA DGX Spark (GB10) nodes with vLLM (TP=2, FP8 KV, MTP) over a RoCE/RDMA link — …☆85Jul 13, 2026Updated 3 months ago
- An in-app browser pane for DeepSeek Harness — real Chrome over CDP, plus rendered previews of local files, markdown and PDFs.☆15Sep 28, 2026Updated 3 weeks 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
- Qwen3.6 27B × DFlash — 30-35 tok/s on NVIDIA DGX Spark (GB10) - LLama.Cpp☆17May 2, 2026Updated 5 months ago
- Working recipe: MiniMax-M3 NVFP4 at tensor-parallel 3 across 3x DGX Spark (GB10/sm_121) with clean tool-calling. Includes the head-node O…☆16Jul 13, 2026Updated 3 months ago
- GLM-5.2 QuantTrio TP=4+DCP2 on 4x NVIDIA DGX Spark (GB10) — tuned and measured under a real agent workload. Adaptive MTP, the indexer law…☆19Aug 24, 2026Updated 2 months ago
- Repo for a ChatBot, with Gradio, Streaming TinyLlama1.1BOpenOrca.gguf on CPU only☆11Dec 13, 2023Updated 2 years 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
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- A 2MB sklearn classifier on consumer CPU beats Cohere's $10M+ 218B MoE on HumanEval☆13Oct 18, 2026Updated last week
- Open Imi is a open source claude desktop alternative for developers, engineers and tech teams to hack MCP's and agents to their own likin…☆10Nov 16, 2025Updated 11 months ago
- CUDA Blackwell performance fork of antirez/ds4 (DeepSeek-V4-Flash): ~4x prefill, ~1.5x decode, continuous batching, weight server, DSpark☆76Sep 4, 2026Updated last month
- keys-DGX-Sparkticus Utimate Power Pack Unleashed (Dual DGX-Sparks Needed)☆43Aug 23, 2026Updated 2 months ago
- Imagination Studio by keys+Wasserman powered by TensorFold: an AI film studio for Mac and NVIDIA DGX Spark. Plan a film like a crew (Slat…☆197Updated this week
- Open quantization tooling for TurboQuant-style low-bit LLM releases, stock GGUF deployment, and Apple Silicon runtime experiments.☆10May 5, 2026Updated 5 months ago
- Testbench for llama.cpp llama-server☆15Aug 20, 2025Updated last year
- Deploy DeepSeek V4 Flash (MoE reasoning model) on dual DGX Spark nodes with 1M token context, InfiniBand, and FP8 KV-cache☆106Aug 20, 2026Updated 2 months ago
- Scripts I use to create Docker images, create config, & run containers for RabbitMQ and Zookeeper+Kafka. Nothing fancy, they just work. :…☆19Mar 20, 2019Updated 7 years 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.
- Code to reproduce the experiments of the ICLR24-paper: "Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging"☆12Oct 14, 2025Updated last year
- kotlin-spring-boot-apache-ignite-example☆12Mar 9, 2019Updated 7 years ago
- Chinese traditional fortune-telling AI skill (BaZi 八字 + Zi Wei Dou Shu 紫微斗数) for Claude Code, Codex, Cursor, Trae and any agent platform.…☆37May 7, 2026Updated 5 months ago
- Let's vibe hardware: create magical things by chatting with AI.☆48Jul 20, 2026Updated 3 months ago
- A gradio web UI for running Large Language Models like LLaMA, llama.cpp, GPT-J, Pythia, OPT, and GALACTICA.☆13Jan 13, 2026Updated 9 months ago
- FlashQLA TileLang GDN kernels ported to NVIDIA Blackwell consumer (GB10 / DGX Spark)☆18Jun 5, 2026Updated 4 months ago
- ☆16Sep 27, 2023Updated 3 years ago
- Toughday2 is a multithreaded performance testing framework that can be used to benchmark remote applications. It was designed with develo…☆19Apr 8, 2024Updated 2 years ago
- Portable personal advisor OS built from Agent Skills☆12Aug 12, 2026Updated 2 months 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.
- GPT-3-based Slack bot that answers legal & compliance questions and recommends relevant contact persons☆17Apr 18, 2021Updated 5 years ago
- Native DeepSeek V4.1 Flash inference across one RTX PRO 6000 and four DGX Spark expert workers☆37Sep 25, 2026Updated last month
- Native red, blue, and purple security-agent harness for CYBER-FROST☆51Oct 5, 2026Updated 3 weeks ago
- NR1 Github allows you to create more context to your entities by having access to the GitHub repository, contributors and README.☆20Jul 16, 2026Updated 3 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
- GLM-5.2 (744B/40B MoE) on a 4× DGX Spark / GB10 (sm_121) cluster: portable Triton sparse-MLA kernels, a data-free expert prune, MTP draft…☆37Aug 20, 2026Updated 2 months ago
- codebase release for EMNLP2023 paper publication☆19Sep 18, 2025Updated last year