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
Alternatives and similar repositories for GLM-5.3-Flash-EXL3-K2-DGX-Spark-recipe
Users that are interested in GLM-5.3-Flash-EXL3-K2-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:
- Qwen3.8-27B on one DGX Spark: SGLang + DFlash2 recipe, engine image, benchmarks, data and charts. By @redp314☆37Sep 6, 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
- Pinned stock Qwen3.8-27B NVFP4 + DFlash2 recipe and measured evidence for one NVIDIA DGX Spark☆21Sep 10, 2026Updated last month
- ☆15Sep 5, 2026Updated last month
- An environment where open models work as agents: a first-level harness with routing, skills, memory and sandboxed tools, on an engine tha…☆54Updated 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.
- ☆53Sep 13, 2026Updated last month
- Pinned, checksum-verified GLM-5.3-Flash EXL3 K2 recipe for one NVIDIA GB10.☆38Updated this week
- All-NVFP4 vLLM + DFlash2 K7 for Blackwell (SM120/SM121): NVFP4 target/draft/KV, 262K context, optional CPU vision sidecar.☆40Aug 28, 2026Updated last month
- Serve Qwen3.8-Flash-Next (turboderp ExLlamaV3 pack) on one NVIDIA DGX Spark with exllamav3☆63Oct 14, 2026Updated last week
- Qwen3.6-27B (NVFP4) DFlash for DGX Spark☆22Jul 31, 2026Updated 2 months ago
- Qwen3.8-Flash-Next on ONE DGX Spark (TP=1)☆610Oct 4, 2026Updated 2 weeks ago
- Local-first AI workbench for OCR, transcription, translation, image generation, mind maps and composable workflows. Built for DGX Spark.☆68Sep 2, 2026Updated last month
- ☆15Sep 14, 2026Updated last month
- Custom inference recipes for NVIDIA DGX Spark — Qwen 122B DFlash hybrid☆89Updated this week
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- 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
- Qwen3.8-27B on one DGX Spark (TensorFold)☆34Oct 1, 2026Updated 2 weeks ago
- Serve Ornith-1.5-35B-A3B (NVFP4 + in-checkpoint MTP, 256k ctx) on one DGX Spark — vLLM b12x recipe plus CUDA-graph fixes.☆32Aug 19, 2026Updated 2 months ago
- qwen38-flash-next recipe for solo GB10☆150Updated this week
- GLM-5.3 EXL3 on DGX Sparks with TensorFold☆25Oct 4, 2026Updated 2 weeks ago
- Verified Qwen3.8 Flash-Next GGUF recipe for one NVIDIA DGX Spark or ASUS Ascent GX10☆60Updated this week
- GLM-5.3-Flash (abliterated EXL3) on 2x NVIDIA DGX Spark with the TensorFold engine: 1.8x faster decode than vLLM, 4x256k concurrent threa…☆115Updated this week
- GLM-5.3-Flash EXL3 (320B MoE) on 2x NVIDIA DGX Spark — production serving kit, 1M context, 97%+ multi-session prefix caching, DFlash2 spe…☆62Oct 5, 2026Updated 2 weeks ago
- qwen38-flash-next recipe for tp=2 GB10☆127Oct 6, 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.
- 8s of H3 video in 2m54s warm delivery on two DGX Sparks. Scene-specific LTX refinement, original-voice restoration, measured sync, clips …☆23Sep 12, 2026Updated last month
- Qwen3.8 Flash Next on one DGX Spark (TensorFold)☆285Updated 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 3 weeks ago
- recipe for running Qwen3.8-Flash-Next on a single DGX Spark☆466Updated this week
- DeepSeek-V4.1-Flash on a single DGX Spark (GB10): resident hot experts + NVMe streaming, DSpark, OpenAI API. Work in progress.☆126Sep 16, 2026Updated last month
- Community registry of LLM serving-path traps that produce confidently wrong measurements: templates, tool parsers, reasoning fields, quan…☆140Updated this week
- 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-…☆128Sep 7, 2026Updated last month
- GLM-5.3 (full) on 3-6 DGX Sparks (GB10): a from-scratch CUDA inference engine☆38Updated this week
- Welcome to the LLM Tutorials and RAG Implementations repository! This repository provides tutorials, guides, and implementations for work…☆13Jul 1, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Fast, capable GLM-5.3-Flash FP4-Local on two DGX Sparks: opinionated Atlas serving and reproducible inference research.☆64Updated this week
- Plain-language web remote control for a fleet of ComfyUI instances (Qwen-Image-2.1 stills, MiniMax-H3 video). Stdlib Python, no dependenc…☆45Oct 9, 2026Updated last week
- GLM-5.3-Flash (NVFP4) at TP=4 across 4x ASUS GX10 / GB10 - vLLM + mentat instead of Ray, 524k context, DFlash2. Minimal working recipe.☆90Updated this week
- Time-boxed passwordless sudo for agents. Grants expire on a systemd timer, validated with visudo before install, audited with sudoreplay.☆27Sep 3, 2026Updated last month
- ComfyUI custom node that composes prompts from multiple image references. Tested with Qwen3.8 27B through native CLIPLoader.☆16Updated this week
- An AI assistant to prioritize security vulnerabilities☆14May 29, 2026Updated 4 months ago
- Identity-first cognitive agent OS with memory, multi-channel ingress, Operating Room orchestration, and desktop surfaces.☆28Sep 30, 2026Updated 3 weeks ago