Pinned one-DGX-Spark Docker recipe for DeepSeek V4 Flash with EXL3, SparkInfer, and 262K NVFP4 MLA KV cache
☆32Sep 6, 2026Updated last month
Alternatives and similar repositories for deepseek-v4-flash-0731-exl3-k2-spark
Users that are interested in deepseek-v4-flash-0731-exl3-k2-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:
- CUDA Blackwell performance fork of antirez/ds4 (DeepSeek-V4-Flash): ~4x prefill, ~1.5x decode, continuous batching, weight server, DSpark☆77Sep 4, 2026Updated last month
- GLM-5.3-Flash EXL3 2.05 on one DGX Spark — TP1 vLLM, DFlash2 K5, concurrency, 262K context, and published fidelity measurements☆53Sep 22, 2026Updated 3 weeks ago
- How @gumclaw is set up — architecture & guardrails☆25Jul 24, 2026Updated 2 months ago
- Entrpi/ds4, a Blackwell CUDA perf fork of antirez/ds4 on NVIDIA DGX Spark: one-command install, ~3x upstream prefill, ~1.5x decode, DSpar…☆410Aug 27, 2026Updated last month
- Rulith Inference, formerly Strix Llama. Serving a 125B MoE model fast on one AMD Strix Halo machine, on Windows: a patched llama.cpp, a m…☆40Updated 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.
- A tiered-memory system design for workloads that don't fit in RAM: measure the working set, pin the hot tier, stream the cold tier from f…☆28Updated this week
- Snaky C2 — Windows EDR evasion & Red Team C2 framework based on Rust & Nim (Indirect Syscalls, KCT injection, LSB Steganography)☆27Jul 27, 2026Updated 2 months ago
- Recipe for the fastest 4bit qwen3.8FlashNext☆65Oct 6, 2026Updated 2 weeks ago
- A static pages server for Gitea☆14Sep 29, 2026Updated 3 weeks ago
- Pinned one-DGX-Spark Docker recipe for DeepSeek V4 Flash with EXL3, SparkInfer, and 262K NVFP4 MLA KV cache☆166Sep 3, 2026Updated last month
- 3D models for DGX cases☆53Aug 14, 2026Updated 2 months ago
- qwen38-flash-next recipe for solo GB10☆157Updated this week
- Serving 4-bit Qwen3.8-27B on a single DGX Spark (GB10): 75 tok/s single-stream, 246 tok/s aggregate at 8-way concurrency. NVFP4 vs MixedI…☆51Sep 29, 2026Updated 3 weeks ago
- ☆49Updated 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.
- CPU speaker diarization with native INT8 kernels. Rust, CLI, Python and C interfaces; no ONNX Runtime in the core.☆20Oct 10, 2026Updated last week
- One command turns a DGX Spark or ASUS Ascent GX10 into a private AI server: seven measured, pinned AI lanes (text up to 1M tokens, images…☆237Updated this week
- Qwen3.8-27B EXL3 (4.00 bpw) + DFlash2 speculative decoding for ExLlamaV3, validated at 262k context on a 24 GB RTX 3090☆25Sep 20, 2026Updated last month
- YOLOv8 Segmentation with Rust☆15Dec 6, 2024Updated last year
- Guarded, recoverable web ChatGPT automation for local Codex projects on Windows and macOS☆52Sep 9, 2026Updated last month
- Heterogeneous prefill/decode for DeepSeek-V4-Flash: CUDA prefill (DGX Spark, vLLM) -> Metal decode (Mac Studio, oMLX) over plain 10GbE☆150Updated this week
- Qwen3.8-Flash-Next on one DGX Spark: tuned vLLM launch, context sweep, tuning ladder. By @redp314☆21Sep 21, 2026Updated last month
- CUDA WebShader FFT water with shallow refraction, sunlight caustics, fly camera and interactive spectral forces☆24Oct 4, 2026Updated 2 weeks ago
- Verified Qwen3.8 Flash-Next GGUF recipe for one NVIDIA DGX Spark or ASUS Ascent GX10☆61Updated 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.
- Xcode Railscasts derived theme☆14Jul 17, 2012Updated 14 years ago
- dockerfiles, compose files, benchmarks for 2x R9700 serving☆26Updated this week
- Qwen3.8-Flash-Next on ONE DGX Spark (TP=1)☆614Oct 4, 2026Updated 2 weeks ago
- Custom inference recipes for NVIDIA DGX Spark — Qwen 122B DFlash hybrid☆89Updated this week
- Turns Apple Podcast Transcript Files (.TTLM) into Readable Text.☆12Feb 12, 2025Updated last year
- Qwen3.8-Flash-Next (180B MoE) on one 12-16 GB NVIDIA GPU, Linux or Windows. Own engine, own compression.☆29Updated this week
- Qwen3.8-27B NVFP4 on SGLang (DGX Spark / SM121): official image pin, native DSpark/EAGLE click-run, matched evals☆21Aug 19, 2026Updated 2 months ago
- Decision Index: reproduce the Jev decision-model benchmark suite locally or as one HF Job☆60Oct 14, 2026Updated last week
- Qwen3.8-27B NVFP4 (W4A16 shipped recipe) + MTP on NVIDIA DGX Spark GB10/SM121 — vLLM v0.27.2rc0, FP8 KV, 262K context, full reproducibili…☆27Aug 20, 2026Updated 2 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Local-first Home Assistant elder-care safety net: 5 paste-ready automations + an optional local AI care agent (digest + urgent alerts). C…☆23Updated this week
- Tool-calling quality benchmark for LLM serving stacks. 80+ deterministic scenarios testing multi-turn orchestration, safety boundaries, a…☆394Updated this week
- A web group chat where Claude, ChatGPT, Grok and Gemini hang out and talk on their own, powered by your logged-in CLIs (no API keys). Eng…☆70Updated this week
- recipe for running Qwen3.8-Flash-Next on a single DGX Spark☆466Updated this week
- AI image generation CLI. One command, one image, three seconds. Gemini-powered.☆18Jul 24, 2026Updated 2 months ago
- ☆14Oct 13, 2026Updated last week
- vLLM recipe: GLM-5.3-Flash EXL3 K2 on one DGX Spark GB10. Native MTP k=2. Measured tok/s.☆26Sep 10, 2026Updated last month