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
Alternatives and similar repositories for deepseek-v41-flash-spark
Users that are interested in deepseek-v41-flash-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:
- An environment where open models work as agents: a first-level harness with routing, skills, memory and sandboxed tools, on an engine tha…☆78Updated this week
- 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
- DeepSeek-V4.1-Flash on 2x NVIDIA DGX Spark with the TensorFold engine: 1.8-1.9x code, 2.5x multi-stream, 1.7-1.95x prefill vs the vLLM ki…☆143Updated this week
- SparkGLM Atlas engine: Enntity's fork of Mango-kid/atlas (Atlas-Inf/atlas), AGPL-3.0☆11Updated this week
- DeepSeek-V4.1-Flash EXL3 vLLM recipe for 2x DGX Spark (GB10)☆28Sep 27, 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.
- Serve Qwen3.8-Flash-Next (turboderp ExLlamaV3 pack) on one NVIDIA DGX Spark with exllamav3☆65Oct 14, 2026Updated last month
- LLM engine with adaptive expert loading. DeepSeek V4.1 Flash (510 GB) on two DGX Sparks at its released MXFP4 weights.Or GLM 5.3 full EXL…☆44Updated this week
- qwen38-flash-next recipe for tp=2 GB10☆134Oct 29, 2026Updated 2 weeks ago
- qwen38-flash-next recipe for solo GB10☆172Oct 30, 2026Updated 2 weeks ago
- glm53-flash recipe for tp=2 GB10☆18Oct 29, 2026Updated 2 weeks ago
- 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
- DeepSeek V4 Flash DSpark DGX Spark TP4 Ring 生产调优与算子工程归档 (LuZ0.4.5)☆17Sep 11, 2026Updated 2 months ago
- Low-latency collective transport and distributed LLM serving stack for switchless GB10 clusters.☆105Nov 2, 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.☆96Nov 6, 2026Updated last week
- 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.
- GLM-5.3-Flash EXL3 K2 2.33bpw on ONE DGX Spark: native MTP (layer 45, 288 experts), CUDA graphs on, full 262,144 ctx. Measured ~19 tok/s …☆10Sep 19, 2026Updated last month
- Three-DGX-Spark TP3 serving recipe for GLM-5.3 Flash☆21Oct 5, 2026Updated last month
- Minimal read-only OS image for GB10 (DGX Spark / ASUS GX10) boxes☆98Updated this week
- Uncensored Qwen3.8-27B Ultimate - BF16 master + NVFP4-MIXED deploy. QuickStarts for DGX Spark (one Dynamic DFlash lattice seat @ util 0.8…☆21Updated this week
- Userland fan control for NVIDIA DGX Spark, with additive RPM floors, a temperature-based curve, Secure Boot signing, and DKMS support.☆51Oct 29, 2026Updated 2 weeks ago
- GLM-5.3-Flash EXL3 (320B MoE) on 2x NVIDIA DGX Spark — production serving kit, 1M context, 97%+ multi-session prefix caching, DFlash2 spe…☆65Nov 4, 2026Updated last week
- ☆16Sep 25, 2026Updated last month
- GLM-5.3-Flash (abliterated EXL3) on 2x NVIDIA DGX Spark with the TensorFold engine: 1.8x faster decode than vLLM, 4x256k concurrent threa…☆123Oct 30, 2026Updated 2 weeks ago
- GLM-5.3 Flash EXL3 for 2-4x DGX Sparks☆760Nov 4, 2026Updated last 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 (Z.ai) NVFP4 (LibertAI) + NVFP4 KV, 1M context on 2x DGX Spark GB10 — vLLM TP2 recipe, walls ledger, benchmarks, needle to …☆29Aug 31, 2026Updated 2 months ago
- Qwen 3.8 125B-A6B CUDA inference speedup benchmark: ds4 engine, overlay, and submission harness☆16Oct 10, 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☆57Sep 22, 2026Updated last month
- DeepSeek v4 Flash EXL3 on one DGX Spark☆351Aug 24, 2026Updated 2 months ago
- ☆19Sep 9, 2026Updated 2 months ago
- CUDA Blackwell performance fork of antirez/ds4 (DeepSeek-V4-Flash): ~4x prefill, ~1.5x decode, continuous batching, weight server, DSpark☆77Oct 26, 2026Updated 2 weeks ago
- Qwen3.8-27B ADay777-Ablit · NVFP4 · A4Q · NVFP4-KV (4M+ pool) · MTP-3 — single DGX Spark (GB10/sm121), eugr vLLM 0.27. 1M ctx @ c=4.☆24Aug 17, 2026Updated 2 months ago
- GLM-5.3-Flash (NVFP4) at TP4 across 4x DGX Spark via a switchless RoCE ring + DFlash2 — reproducible recipe☆112Oct 25, 2026Updated 2 weeks ago
- DeepSeek v4.1 Flash EXL3 2.9 bpw for 2x DGX Sparks☆284Sep 19, 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.
- Fast, capable GLM-5.3-Flash FP4-Local on two DGX Sparks: opinionated Atlas serving and reproducible inference research.☆73Updated this week
- W4A4 full（VLLM_MOE_W4A4=2）+ （VLLM_B12X_SHARED_WRAPPER=1）+ FlashInfer 0.6.16 + threshold 4096 + util 0.78 + DSpark MTP n7 + CUMEM=0☆16Aug 26, 2026Updated 2 months ago
- Qwen3.8-Flash-Next on ONE DGX Spark (TP=1)☆637Oct 4, 2026Updated last month
- Local diagnostic CLI for NVIDIA DGX Spark (GB10). Detects power caps, UMA pressure, thermal risk, CUDA 13/SM_121 wheel mismatches, Docker…☆166Oct 22, 2026Updated 3 weeks 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…☆414Aug 27, 2026Updated 2 months ago
- GLM-5.3-Flash EXL3 on 2x DGX Spark with TensorFold☆529Nov 4, 2026Updated last week
- Recover usable memory on DGX Spark with a 64 KiB kernel: an opt-in NVIDIA UVM page-table packing patch, build tools, and measured validat…☆39Oct 16, 2026Updated 3 weeks ago
Are these results useful?