MiMo-V2.5 NVFP4 4-bit weights + NVFP4 4-bit KV cache + DFlash speculative decoding on 2× NVIDIA DGX Spark — 1M context, 3.4M-token KV pool
☆17Jul 13, 2026Updated this week
Alternatives and similar repositories for MiMo-V2.5-DFlash-1M-ctx-NVFP4-KV-2x-DGX-Spark
Users that are interested in MiMo-V2.5-DFlash-1M-ctx-NVFP4-KV-2x-DGX-Spark 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…☆26Updated this week
- 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…☆36Updated this week
- 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…☆19Jul 7, 2026Updated last week
- ☆115Updated this week
- Live dashboard: fire N parallel streaming coding-agent runs at any OpenAI-compatible endpoint — per-run TTFT/tok-s/E2E, real kill switch,…☆17Jul 8, 2026Updated last week
- 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.
- Deploy DeepSeek V4 Flash (MoE reasoning model) on dual DGX Spark nodes with 1M token context, InfiniBand, and FP8 KV-cache☆77Updated this week
- 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) /…☆24Jul 7, 2026Updated last week
- DeepSeek V4 Flash @ 1M token context on 2x NVIDIA DGX Spark — production-tested recipe (45 tok/s decode, real 800K prompts served)☆34Updated this week
- DeepSeek V4 Flash DSpark 1M NVFP4 KV recipe for 2x DGX Spark☆134Updated this week
- llama-server start/stop scripts for Qwen3.6-35B-A3B UD-Q8_K_XL GGUF on DGX Spark☆24Jul 6, 2026Updated last week
- DeepSeek-V4-Flash-DSpark abliterated (uncensored) · ~100% refusal bypass · C1 ~57 tok/s · 1M ctx · 2× DGX Spark · HF weights☆21Updated this week
- Production-ready vLLM deployment wrapper for Qwen3.6-27B (NVFP4) — self-hosted OpenAI-compatible inference☆44Jul 1, 2026Updated last week
- 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…☆42Jun 28, 2026Updated 2 weeks ago
- Run the AEON Bench suite on your own hardware: verified HuggingFace pull → serve → benchmark (text · agentic ×3 harnesses · vision · audi…☆20Updated 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.
- Local diagnostic CLI for NVIDIA DGX Spark (GB10). Detects power caps, UMA pressure, thermal risk, CUDA 13/SM_121 wheel mismatches, Docker…☆90Updated this week
- Let any AI agent run DaVinci Resolve — MCP server with live Studio control, free-edition FCPXML/LUT workflows, reference color matching, …☆17Updated this week
- DFlash vLLM for DGX Spark — Plug & Play Block-Diffusion Speculative Decoding☆52Jun 28, 2026Updated 2 weeks ago
- Uncensored/abliterated Ornith-1.0-35B (AEON Ultimate): 0% refusal, 0 coding-capability loss. BF16 + FP8 for vLLM.☆63Jun 29, 2026Updated 2 weeks ago
- Deploy concurrent Hermes Agent workers on unified-memory GPUs (GB10, DGX Spark) for maximum total tok/s. Profile-isolated, kanban-coordin…☆71Updated this week
- Redmine's plugin to allow to assign an SLA by issue priority and project☆11Nov 28, 2019Updated 6 years ago
- Head-to-head comparison of local LLMs for agentic workflows (Hermes Agent, tool-eval-bench)☆29Jul 6, 2026Updated last week
- JavaScript component to parse, clean, remove formatting (unformat) numbers in strings.☆10Dec 5, 2024Updated last year
- AI Liquidity Management Agent☆13Jan 19, 2026Updated 5 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.
- ☆15Aug 16, 2023Updated 2 years ago
- ☆19Jun 16, 2026Updated 3 weeks ago
- Libraries and code for Starlight board☆12Dec 23, 2023Updated 2 years ago
- ☆19Nov 17, 2022Updated 3 years ago
- Wasserman's Filmmaker Suite — Blockout, Motion Previs Studio, Stem Studio, and the Unofficial DaVinci MCP: AI-native filmmaking from firs…☆38Updated this week
- 18-channel, 40-nm FWHM spectrometer☆22Nov 30, 2020Updated 5 years ago
- ConfigMgr LogFiler Opener automates the usage of CMTrace, CMLogViewer and OneTrace for opening single or multiple ConfigMgr Client Logfil…☆13May 22, 2023Updated 3 years ago
- Show PIM role to solve a task - and group to activate the needed permission☆15May 22, 2025Updated last year
- Git-backed long-term memory for AI coding agents☆73May 25, 2026Updated last month
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Query model running with Ollama from within Claude Desktop or other MCP clients☆33Feb 5, 2025Updated last year
- Go implementation of bcrypt_pbkdf(3) from OpenBSD☆15Jun 27, 2026Updated 2 weeks ago
- An MCP server that provides persistent memory capabilities through a local knowledge graph, enabling AI assistants to maintain context ac…☆22Dec 20, 2025Updated 6 months ago
- Self Hosted Dashboard for Honcho☆22Jun 6, 2026Updated last month
- A dedicated effort to make an optimized, bleeding edge vLLM image using Docker to support DGX comprehensively☆122Feb 22, 2026Updated 4 months ago
- Load software onto a Commodore 64 or Commodore Vic-20 retro-computer via a web browser with the help of an Arduino / clone microcontrolle…☆11Sep 25, 2024Updated last year
- reStructuredText in C☆13May 20, 2023Updated 3 years ago