DeepSeek V4 Flash DSpark 1M NVFP4 KV recipe for 2x DGX Spark
☆482Sep 10, 2026Updated last week
Alternatives and similar repositories for DeepSeek-v4-Flash-Vision-Exp-DSpark-1M-NVFP4-KV-2x-DGX-Spark
Users that are interested in DeepSeek-v4-Flash-Vision-Exp-DSpark-1M-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:
- Self-contained DeepSeek V4 Flash DSpark TP=2 recipe for 2x DGX Spark with 62 tok/s benchmark☆24Jul 13, 2026Updated 2 months ago
- 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…☆46Jul 13, 2026Updated 2 months 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 last month
- Live dashboard: fire N parallel streaming coding-agent runs at any OpenAI-compatible endpoint — per-run TTFT/tok-s/E2E, real kill switch,…☆27Jul 23, 2026Updated 2 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 — …☆83Jul 13, 2026Updated 2 months ago
- 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.
- Recipe: GLM-5.2 (unpruned QuantTrio Int4-Int8Mix) at 200K ctx with MTP spec decode on a 4x NVIDIA DGX Spark (GB10) cluster☆77Jul 25, 2026Updated last month
- DeepSeek-V4-Flash-DSpark abliterated (uncensored) · ~100% refusal bypass · C1 ~57 tok/s · 1M ctx · 2× DGX Spark · HF weights☆49Aug 17, 2026Updated last month
- Official Spark Arena Recipe Registry☆63Sep 3, 2026Updated 2 weeks 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 2 months ago
- DeepSeek V4 Flash @ 1M token context on 2x NVIDIA DGX Spark — production-tested recipe (45 tok/s decode, real 800K prompts served)☆36Jul 13, 2026Updated 2 months ago
- Docker configuration for running VLLM on dual DGX Sparks☆2,298Updated this week
- Recipe: GLM-5.2 (unpruned QuantTrio Int4-Int8Mix) at 655,360-token context + MTP spec decode (DCP4, fp8_ds_mla) on a 4x NVIDIA DGX Spark …☆31Jul 13, 2026Updated 2 months ago
- sparkrun - launch, manage, and stop LLM inference workloads on NVIDIA DGX Spark systems. Live support: https://discord.com/invite/GH5kRg…☆514Updated this week
- vLLM 0.25.1 serving stack for poolside/Laguna-S-2.1-NVFP4 with DFlash speculative decoding — DGX Spark & RTX 6000 PRO☆83Jul 22, 2026Updated 2 months ago
- 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.
- Profile repo — categorized index of NVFP4 model releases, DGX Spark inference stacks, Apple Silicon MLX builds, the voice-AI stack, and t…☆40Sep 15, 2026Updated last week
- Uncensored/abliterated Ornith-1.0-35B (AEON Ultimate): 0% refusal, 0 coding-capability loss. BF16 + FP8 for vLLM.☆82Jun 29, 2026Updated 2 months ago
- llama-server start/stop scripts for Qwen3.6-35B-A3B UD-Q8_K_XL GGUF on DGX Spark☆27Jul 6, 2026Updated 2 months ago
- Mixed-precision quantization for LLMs. Every layer refracts into a different format based on its sensitivity. Native compressed-tensors e…☆103Updated this week
- Setup wizard for Hermes Gateway Desktop☆32Jul 2, 2026Updated 2 months ago
- vLLM + Qwen3.5-122B-A10B-NVFP4 on NVIDIA DGX Spark (GB10/SM121) — single-GPU NVFP4 W4A4 with MTP speculative decoding, self-contained Doc…☆41Mar 12, 2026Updated 6 months ago
- Serve GLM-5.2 469B (REAP-pruned, NVFP4) across 3× NVIDIA DGX Spark with vLLM pipeline parallelism — 256K context, production-ready config…☆34Jul 12, 2026Updated 2 months ago
- Deploy concurrent Hermes Agent workers on unified-memory GPUs (GB10, DGX Spark) for maximum total tok/s. Profile-isolated, kanban-coordin…☆81Jul 18, 2026Updated 2 months ago
- Pure Rust Inference Engine☆699Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆20Jul 21, 2026Updated 2 months ago
- my version of the models dev site which is way faster and has the filters I want☆18Apr 22, 2026Updated 5 months ago
- llama-benchy - llama-bench style benchmarking tool for all backends☆732Jul 10, 2026Updated 2 months ago
- Ember addon to configure Netlify headers and redirects☆15Mar 4, 2023Updated 3 years ago
- ☆259Updated this week
- Sglang LLM Inference: RTX Pro 6000 vs DGX Spark☆22Oct 18, 2025Updated 11 months ago
- vLLM + Qwen3.6-27B (BF16) OpenAI-compatible inference server on AMD Strix Halo (Ryzen AI Max+ 395, gfx1151). Vision input, 256K context, …☆18Apr 26, 2026Updated 4 months ago
- A vLLM patch + hand‑written SM120 SASS kernels: 2‑bit MoE experts + an FP4 "delta" cache that recovers precision — matching the official …☆539Updated this week
- Run vLLM on 1-to-N NVIDIA DGX Spark servers (single Spark, 2 via direct cable, or 3+ via switched fabric) to serve or benchmark LLMs☆129Jun 22, 2026Updated 3 months ago
- 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.
- ☆39Jul 17, 2026Updated 2 months ago
- Run the AEON Bench suite on your own hardware: verified HuggingFace pull → serve → benchmark (text · agentic ×3 harnesses · vision · audi…☆27Sep 11, 2026Updated last week
- A dedicated effort to make an optimized, bleeding edge vLLM image using Docker to support DGX comprehensively☆125Feb 22, 2026Updated 7 months ago
- DeepSeek 4 Flash local inference engine for Metal☆63May 15, 2026Updated 4 months ago
- Local AI workstation — discover, run, chat, benchmark, and generate images from open-weight models. DFlash/DDTree speculative decoding, T…☆25Sep 4, 2026Updated 2 weeks ago
- Convert java 11 JFR to folded format for https://github.com/brendangregg/FlameGraph☆12May 23, 2019Updated 7 years ago
- [RAL 2026] GSO-SLAM☆27Jun 20, 2026Updated 3 months ago