DeepSeek-v4-Flash 0731 recipe for 2x DGX Sparks
☆914Aug 23, 2026Updated this week
Alternatives and similar repositories for DeepSeek-v4-Flash-DSpark-2x-DGX-Spark
Users that are interested in DeepSeek-v4-Flash-DSpark-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:
- DeepSeek V4 Flash DSpark 1M NVFP4 KV recipe for 2x DGX Spark☆422Updated this week
- Deploy DeepSeek V4 Flash (MoE reasoning model) on dual DGX Spark nodes with 1M token context, InfiniBand, and FP8 KV-cache☆103Updated 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…☆21Aug 17, 2026Updated last 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…☆42Jul 13, 2026Updated last month
- sparkDash ⚡ — Multi-DGX Spark Monitoring Dashboard☆280Updated this 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.
- vLLM 0.25.1 serving stack for poolside/Laguna-S-2.1-NVFP4 with DFlash speculative decoding — DGX Spark & RTX 6000 PRO☆80Jul 22, 2026Updated last month
- 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 — …☆71Jul 13, 2026Updated last month
- Recipe: GLM-5.2 (unpruned QuantTrio Int4-Int8Mix) at 200K ctx with MTP spec decode on a 4x NVIDIA DGX Spark (GB10) cluster☆74Jul 25, 2026Updated 3 weeks ago
- llama-server start/stop scripts for Qwen3.6-35B-A3B UD-Q8_K_XL GGUF on DGX Spark☆27Jul 6, 2026Updated last month
- AEON vLLM Ultimate — vLLM 0.27.1 built from source for DGX Spark / Blackwell (sm_121a/GB10). DSpark quantized Markov heads, DFlash SWA on…☆123Updated 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 …☆30Jul 13, 2026Updated last month
- Head-to-head comparison of local LLMs for agentic workflows (Hermes Agent, tool-eval-bench)☆34Jul 6, 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…☆451Jul 3, 2026Updated last month
- ☆37Jul 17, 2026Updated last month
- 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.
- Uncensored/abliterated Ornith-1.0-35B (AEON Ultimate): 0% refusal, 0 coding-capability loss. BF16 + FP8 for vLLM.☆75Jun 29, 2026Updated last month
- sparkrun - launch, manage, and stop LLM inference workloads on NVIDIA DGX Spark systems☆461Updated this week
- Tool-calling quality benchmark for LLM serving stacks. 80+ deterministic scenarios testing multi-turn orchestration, safety boundaries, a…☆299Updated this week
- Profile repo — categorized index of NVFP4 model releases, DGX Spark inference stacks, Apple Silicon MLX builds, the voice-AI stack, and t…☆39Jul 9, 2026Updated last month
- Setup wizard for Hermes Gateway Desktop☆31Jul 2, 2026Updated last month
- Official Spark Arena Recipe Registry☆61Aug 15, 2026Updated last week
- Qwen3.5-122B-A10B on DGX Spark: 28.3 → 51 tok/s (+80%)☆312Updated this week
- Collection of step-by-step playbooks for setting up AI/ML workloads on NVIDIA DGX Spark devices with Blackwell architecture.☆1,288Jul 29, 2026Updated 3 weeks ago
- Mixed-capability LLM benchmark for DGX Spark — 57 scenarios, 10 domains, partial-credit grading, trial statistics☆155Updated this week
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Live dashboard: fire N parallel streaming coding-agent runs at any OpenAI-compatible endpoint — per-run TTFT/tok-s/E2E, real kill switch,…☆25Jul 23, 2026Updated last month
- A vLLM patch + hand‑written SM120 SASS kernels: 2‑bit MoE experts + an FP4 "delta" cache that recovers precision — matching the official …☆527Updated this week
- A dedicated effort to make an optimized, bleeding edge vLLM image using Docker to support DGX comprehensively☆124Feb 22, 2026Updated 6 months ago
- Some benchmark results of small models and quants that fit on DGX Spark☆50Aug 12, 2026Updated last week
- Serve GLM-5.2 469B (REAP-pruned, NVFP4) across 3× NVIDIA DGX Spark with vLLM pipeline parallelism — 256K context, production-ready config…☆33Jul 12, 2026Updated last month
- ☆84Updated this week
- Qwen3.6-35B-A3B-heretic NVFP4 + DFlash speculative decoding on DGX Spark (GB10/sm_121a). Source-built vLLM image + 7 patches + comprehens…☆136Jun 28, 2026Updated last month
- ☆17Aug 13, 2026Updated last week
- FlashQLA TileLang GDN kernels ported to NVIDIA Blackwell consumer (GB10 / DGX Spark)☆17Jun 5, 2026Updated 2 months ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- Entrpi/ds4, a Blackwell CUDA perf fork of antirez/ds4 on NVIDIA DGX Spark: one-command install, ~3x upstream prefill, ~1.5x decode, DSpar…☆370Updated this week
- Libegpu is a library for enumerating eGPU devices & enclosures.☆17Nov 24, 2025Updated 9 months ago
- Deploy concurrent Hermes Agent workers on unified-memory GPUs (GB10, DGX Spark) for maximum total tok/s. Profile-isolated, kanban-coordin…☆79Jul 18, 2026Updated last month
- Pure Rust Inference Engine☆659Updated this week
- Wasserman's Filmmaker Suite — ScriptBreak, Cork Board, Master Canvas, Blockout, Motion Previs Studio, Storyboard Reference Studio, Circle…☆119Aug 6, 2026Updated 2 weeks ago
- llama-benchy - llama-bench style benchmarking tool for all backends☆667Jul 10, 2026Updated last month
- Docker/podman container for llama.cpp/vllm/exllamav{2,3} orchestrated using llama-swap☆18Jun 17, 2026Updated 2 months ago