GLM-5.3-Flash NVFP4 on 4x NVIDIA DGX Spark: vLLM TP4, DFlash2 adaptive draft, measured FP8 vs NVFP4 vs EXL3 vs SGLang
☆37Sep 29, 2026Updated 2 weeks ago
Alternatives and similar repositories for GLM-5.3-Flash-4x-DGX-Spark-TP4
Users that are interested in GLM-5.3-Flash-4x-DGX-Spark-TP4 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Run DeepSeek-V4-Flash at full 1M context AND two MiniMax H3 video instances on the same two DGX Sparks. Benchmarked C1-C6.☆35Aug 7, 2026Updated 2 months ago
- Switchless RoCE collectives, NCCL profiles and fabric tooling for DGX Spark inference recipes☆37Updated this week
- GLM-5.3-Flash (320B MoE) at TP4 across four DGX Sparks, same day as the model drop: 36 tok/s, 1.26M-token FP8 KV pool, 262K context, MTP …☆57Oct 10, 2026Updated last week
- GLM-5.3 (full) on 3-6 DGX Sparks (GB10): a from-scratch CUDA inference engine☆37Updated 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
- 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.
- GLM-5.3-Flash (NVFP4) at TP=4 across 4x ASUS GX10 / GB10 - vLLM + mentat instead of Ray, 524k context, DFlash2. Minimal working recipe.☆89Updated this week
- A curated list of awesome local AI projects and repos☆46Updated this week
- DeepSeek-V4-Flash-DSpark optimized vLLM 0.26.0 SM121 dual-GB10 evidence (NVFP4 KV, B12X, DSpark K6)☆31Aug 3, 2026Updated 2 months ago
- GLM-5.3-Flash EXL3 on 2x DGX Spark with TensorFold☆457Updated this week
- DeepSeek-V4.1-Flash on 3-4x NVIDIA DGX Sparks☆247Updated this week
- Give DeepSeek V4 Flash eyes. OpenAI-compatible shim + tiny local VLM. Point any harness at one URL and your text-only model accepts image…☆30Aug 9, 2026Updated 2 months ago
- MiniMax-H3 on single DGX Spark: keys Sol-Engine ports + Heretic TE + Spectrum/Sage speed + 0.5MP upscaler finish. Formal bench included.☆49Aug 23, 2026Updated last month
- Minimal read-only OS image for GB10 (DGX Spark / ASUS GX10) boxes☆89Oct 4, 2026Updated 2 weeks ago
- 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
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- GLM-5.3-Flash (NVFP4) on 2x NVIDIA DGX Spark - vLLM TP2, 262K context, MTP. World-first deploy recipe: 7 day-0 bugs found and fixed, patc…☆236Sep 30, 2026Updated 2 weeks ago
- GLM-5.3-Flash (NVFP4) at TP4 across 4x DGX Spark via a switchless RoCE ring + DFlash2 — reproducible recipe☆108Updated 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
- Measured SM121 compatibility recipe for MiniMax H3 FL2VA on one NVIDIA DGX Spark with vLLM-Omni and online FP8.☆61Aug 4, 2026Updated 2 months ago
- DeepSeek-V4.1-Flash (552B MoE, MXFP4 experts, 1M ctx) on four NVIDIA DGX Sparks with vLLM TP4: Engram-on-disk patch, sm121 kernel build, …☆110Updated this week
- MiMo-V2.5 NVFP4 4-bit weights + NVFP4 4-bit KV cache + DFlash speculative decoding on 2× NVIDIA DGX Spark — 1M context, 3.4M-token KV poo…☆18Jul 13, 2026Updated 3 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 2 months ago
- GLM-5.3 Flash EXL3 for 2-4x DGX Sparks☆736Updated this week
- 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
- 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.
- 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…☆44Jul 13, 2026Updated 3 months ago
- Decision engine☆51Sep 24, 2026Updated 3 weeks ago
- Autonomous self-improving 4x DGX Spark (GB10) MoA stack + LoRA loop (DSV4F router, Qwen3.6/Omni/TwoTower/Gemma). Hermes MoA routing, ~90%…☆24Aug 17, 2026Updated 2 months ago
- An GB10-optimized inference engine☆108Updated this week
- Qwen3.8-Flash-Next-NVFP4-vLLM-Dual-DGX-Spark☆411Sep 29, 2026Updated 2 weeks ago
- GLM-5.3-Flash (abliterated EXL3) on 2x NVIDIA DGX Spark with the TensorFold engine: 1.8x faster decode than vLLM, 4x256k concurrent threa…☆115Oct 5, 2026Updated last week
- Optimized inference for the DGX Spark and spark clusters☆123Updated this week
- LLM Inference Engine for Metal and CUDA.☆1,375Updated this week
- English guide + one-command patcher for the vLLM spin-wait bug that overheats NVIDIA DGX Spark / GB10. Credit: nacyot. CPU cores spin at …☆24Aug 17, 2026Updated 2 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Community registry of LLM serving-path traps that produce confidently wrong measurements: templates, tool parsers, reasoning fields, quan…☆135Updated this week
- A collection of AI agent skills for QEMU hardware modeling☆58Jul 28, 2026Updated 2 months ago
- Event-driven long-horizon memory for real-time wearable AI and LLM agents.☆30Aug 18, 2026Updated 2 months ago
- qwen38-flash-next recipe for tp=2 GB10☆127Oct 6, 2026Updated last week
- keys-DGX-Sparkticus Utimate Power Pack Unleashed (Dual DGX-Sparks Needed)☆43Aug 23, 2026Updated last month
- P2P support for nvidia consumer cards☆23Sep 5, 2026Updated last month
- 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