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 — Docker image, launch scripts, RDMA/NCCL setup, and the gotchas.
☆51Jul 13, 2026Updated this week
Alternatives and similar repositories for Deepseek-v4-Flash-TP2-DGX-Spark-500k-CTX
Users that are interested in Deepseek-v4-Flash-TP2-DGX-Spark-500k-CTX are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Deploy DeepSeek V4 Flash (MoE reasoning model) on dual DGX Spark nodes with 1M token context, InfiniBand, and FP8 KV-cache☆77Updated this week
- ☆115Updated this week
- DeepSeek V4 Flash DSpark 1M NVFP4 KV recipe for 2x DGX Spark☆134Updated this week
- 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
- 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 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.
- Recipe: GLM-5.2 (unpruned QuantTrio Int4-Int8Mix) at 200K ctx with MTP spec decode on a 4x NVIDIA DGX Spark (GB10) cluster☆51Updated this week
- 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
- Self-contained DeepSeek V4 Flash DSpark TP=2 recipe for 2x DGX Spark with 62 tok/s benchmark☆22Updated this week
- Mixed-capability LLM benchmark for DGX Spark — 57 scenarios, 10 domains, partial-credit grading, trial statistics☆128Updated this 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
- Production-ready vLLM deployment wrapper for Qwen3.6-27B (NVFP4) — self-hosted OpenAI-compatible inference☆44Jul 1, 2026Updated last week
- Profile repo — categorized index of NVFP4 model releases, DGX Spark inference stacks, Apple Silicon MLX builds, the voice-AI stack, and t…☆36Updated 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
- Setup wizard for Hermes Gateway Desktop☆30Jul 2, 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.
- Native MLX quants of Qwen3.6-27B-AEON-Ultimate-Uncensored for Apple Silicon (Metal): 8-bit, FP4, and MTP self-speculation. Preserves the …☆35Jun 28, 2026Updated 2 weeks ago
- A tool that allows the agent to change its reasoning levels.☆21May 28, 2026Updated last month
- A native /slop-review window for Claude Code, Codex CLI, and pi — review the slop before you ship it. Monaco-powered inline comments, age…☆46Jun 26, 2026Updated 2 weeks ago
- sparkrun - launch, manage, and stop LLM inference workloads on NVIDIA DGX Spark systems☆383Updated this week
- Deploy concurrent Hermes Agent workers on unified-memory GPUs (GB10, DGX Spark) for maximum total tok/s. Profile-isolated, kanban-coordin…☆71Updated this week
- Wasserman's Filmmaker Suite — Blockout, Motion Previs Studio, Stem Studio, and the Unofficial DaVinci MCP: AI-native filmmaking from firs…☆38Updated this week
- DeepSeek V4 Flash specific inference engine. SSD MoE expert paging (slot-bank) + disk KV cache for long agent sessions. Metal-first, narr…☆27Jun 29, 2026Updated 2 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…☆19Jul 7, 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
- 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.
- DGX Spark / GB10 vLLM image for Gemma 4 31B Deckard Heretic Uncensored NVFP4 with z-lab DFlash speculative decoding.☆32May 15, 2026Updated last month
- Fully uncensored, capability-enhanced abliteration of Qwen3.6-27B. NVFP4 + z-lab DFlash speculative decoding (n=12) on the unified ghcr.i…☆416Jul 3, 2026Updated last week
- ☆23Aug 1, 2025Updated 11 months ago
- Head-to-head comparison of local LLMs for agentic workflows (Hermes Agent, tool-eval-bench)☆29Jul 6, 2026Updated last week
- Unlock the true power of DevinCLI with all the of the resources I have gathered for you☆15Jun 1, 2026Updated last month
- map names to localhost ports, made for agents and humans☆18Jul 2, 2026Updated last week
- Template for deploying Workers for Platforms with subdomain routing and custom hostnames☆49Dec 18, 2025Updated 6 months ago
- ☆15Updated 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
- 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.
- Qwen3.6-35B-A3B-heretic NVFP4 + DFlash speculative decoding on DGX Spark (GB10/sm_121a). Source-built vLLM image + 7 patches + comprehens…☆118Jun 28, 2026Updated 2 weeks ago
- ☆44Jun 25, 2025Updated last year
- Framework for building sophisticated Investment Research AI agents .☆23Mar 29, 2026Updated 3 months ago
- DeepSeek 4 Flash local inference engine for Metal☆63May 15, 2026Updated last month
- Main Open-LLM-VTuber has been moved to Open-LLM-VTuber/Open-LLM-VTuber. This repo is Yi-Ting's own lab/workspace for Open-LLM-VTuber and …☆39Feb 14, 2026Updated 5 months ago
- Open source, clear, transparent, real world llm benchmarks☆41Updated this week
- Web UI for sparkrun — launch and monitor inference workloads on NVIDIA DGX Spark☆20Jun 16, 2026Updated 3 weeks ago