Serve DeepSeek-V4-Flash-Vision EXL3 MixedK (full 256 experts) on one NVIDIA DGX Spark with vLLM — recipe, loader patches, and receipts
☆14Sep 7, 2026Updated 2 months ago
Alternatives and similar repositories for DeepSeek-V4-Flash-Vision-EXL3-MixedK-DGX-Spark-recipe
Users that are interested in DeepSeek-V4-Flash-Vision-EXL3-MixedK-DGX-Spark-recipe are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- vLLM recipe: GLM-5.3-Flash EXL3 K2 on one DGX Spark GB10. Native MTP k=2. Measured tok/s.☆26Sep 10, 2026Updated 2 months ago
- 1 spark glm 5.3 flash☆11Sep 7, 2026Updated 2 months ago
- Serve Qwen3.8-Flash-Next (turboderp ExLlamaV3 pack) on one NVIDIA DGX Spark with exllamav3☆65Oct 14, 2026Updated 3 weeks ago
- 🚗 LIMCARS Local Inference Monitor · Cost Analyzer · Recipe Server☆13Nov 5, 2026Updated last week
- An environment where open models work as agents: a first-level harness with routing, skills, memory and sandboxed tools, on an engine tha…☆77Updated 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.
- GLM-5.3-Flash EXL3 2.05 on one DGX Spark — TP1 vLLM, DFlash2 K5, concurrency, 262K context, and published fidelity measurements☆57Sep 22, 2026Updated last month
- Qwen3.8-27B on one DGX Spark: SGLang + DFlash2 recipe, engine image, benchmarks, data and charts. By @redp314☆37Sep 6, 2026Updated 2 months ago
- A community-owned map of LLM inference engine configurations — benchmarks, evals and coverage gaps, hosted on GitHub Pages. The repo is t…☆16Oct 19, 2026Updated 3 weeks ago
- Qwen3.8-27B on one DGX Spark GB10: DFlash 2 for 65 tok/s C1 and 120 C4; EAGLE 3/1/4 for ~191 C8, ~330 C16 and ~535 C32; native 262K, pinn…☆13Oct 6, 2026Updated last month
- Plain-language web remote control for a fleet of ComfyUI instances (Qwen-Image-2.1 stills, MiniMax-H3 video). Stdlib Python, no dependenc…☆47Oct 9, 2026Updated last month
- Agentic test batteries for local models via Hermes Agent - scripted tools + real Hermes CLI sessions☆15Aug 14, 2026Updated 2 months ago
- Supply-chain auditor for (abliterated) GGUF & .safetensor models: chat-template tamper detection, tensor fingerprints, plain-language rep…☆12Oct 15, 2026Updated 3 weeks ago
- Pinned one-DGX-Spark Docker recipe for DeepSeek V4 Flash with EXL3, SparkInfer, and 262K NVFP4 MLA KV cache☆31Sep 6, 2026Updated 2 months ago
- A local-first AI companion that keeps watching while nobody is talking, so it can tell you what you were doing five minutes ago. Runs ent…☆10Jul 29, 2026Updated 3 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.
- ☆55Sep 13, 2026Updated last month
- ☆16Sep 25, 2026Updated last month
- DSV4.1-Flash-1017 SAGE EXL3 (1.62 bpw) on one DGX Spark with vLLM: DSpark MTP, cold-expert ATS alias, tile-K 16 MoE, memory guard, measur…☆42Nov 4, 2026Updated last week
- Local-first AI workbench for OCR, transcription, translation, image generation, mind maps and composable workflows. Built for DGX Spark.☆70Sep 2, 2026Updated 2 months ago
- How I tune a cloned Drama 3 voice so spoken replies sound like talking, not reading☆15Oct 26, 2026Updated 2 weeks ago
- 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 last month
- Qwen3.8-Flash-Next (NVFP4) on DGX Spark in vLLM: one Spark 43.9 tok/s with our disk-backed n-gram table patch, staged gather and reduced-…☆137Sep 7, 2026Updated 2 months ago
- Community registry of LLM serving-path traps that produce confidently wrong measurements: templates, tool parsers, reasoning fields, quan…☆174Updated this week
- Serve typed-decision (System 1) models — Laya or your own — on NVIDIA GPUs or Apple Silicon, with a Jev-compatible API and coding-agent i…☆35Sep 24, 2026Updated last month
- 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.
- Verified Qwen3.8 Flash-Next GGUF recipe for one NVIDIA DGX Spark or ASUS Ascent GX10☆60Updated 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
- A very-low-resource API-compatible replacement for Ray☆13Nov 1, 2026Updated last week
- A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative…☆11Updated this week
- Pinned stock Qwen3.8-27B NVFP4 + DFlash2 recipe and measured evidence for one NVIDIA DGX Spark☆21Updated this week
- DeepSeek-V4.1-Flash on a single DGX Spark (GB10): resident hot experts + NVMe streaming, DSpark, OpenAI API. Work in progress.☆128Sep 16, 2026Updated last month
- Train Embedding Models on MLX.☆17Jun 2, 2026Updated 5 months ago
- Qwen3.8-Flash-Next on ONE DGX Spark (TP=1)☆633Oct 4, 2026Updated last month
- Chezmoi-managed dot files☆12Updated this 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.
- DeepSeek v4 Flash EXL3 on one DGX Spark☆350Aug 24, 2026Updated 2 months ago
- Model-agnostic LLM benchmarking + tuning in one command. A model is a 15-key profile file. Built in production on a 4x NVIDIA DGX Spark c…☆10Sep 16, 2026Updated last month
- An update to the old simple-calc☆10Dec 22, 2025Updated 10 months ago
- Pinned one-DGX-Spark Docker recipe for DeepSeek V4 Flash with EXL3, SparkInfer, and 262K NVFP4 MLA KV cache☆167Sep 3, 2026Updated 2 months ago
- Welcome to the LLM Tutorials and RAG Implementations repository! This repository provides tutorials, guides, and implementations for work…☆13Jul 1, 2025Updated last year
- A 2MB sklearn classifier on consumer CPU beats Cohere's $10M+ 218B MoE on HumanEval☆13Oct 18, 2026Updated 3 weeks ago
- Serving Qwen3.8-27B-FP8 on a single DGX Spark (GB10): 7.88 to 58.5 tok/s single-stream from decode strategy alone, weights untouched. Spe…☆56Sep 29, 2026Updated last month
Are these results useful?