Fastest measured Qwen3.8-27B config for DGX Spark (GB10): SGLang + NVFP4 + DFlash2, 71.4 tok/s greedy median, 1M context, deterministic boots. Flash-Next 176B on one box. One command, everything pinned, and a local cockpit to drive it.
☆228Oct 17, 2026Updated this week
Alternatives and similar repositories for dgx-spark-qwen38
Users that are interested in dgx-spark-qwen38 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Custom inference recipes for NVIDIA DGX Spark — Qwen 122B DFlash hybrid☆81Updated 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
- recipe for running Qwen3.8-Flash-Next on a single DGX Spark☆455Updated this 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
- 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
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Qwen 3.8 27B at 48-65 tok/s on a Mac Studio M4 Max — measured oMLX native-MTP recipe, same-day A/B vs mlx-vlm+MTP sidecar, raw benchmark …☆68Aug 21, 2026Updated last month
- DeepSeek v4 Flash EXL3 on one DGX Spark☆347Aug 24, 2026Updated last month
- GLM-5.3-Flash (NVFP4) at TP4 across 4x DGX Spark via a switchless RoCE ring + DFlash2 — reproducible recipe☆106Updated this week
- Qwen3.8 Flash Next on one DGX Spark (TensorFold)☆263Updated this week
- Strata fork: Qwen3.8-Flash-Next 125B MoE in NVFP4 on one RTX 20-50 card (12 GB+) and 64 GB of RAM or more. Setup installs our GPTQ quants…☆160Updated this week
- Oído: open-vocabulary speech recognition that fits in a $5 ESP32-S3. 3.7% LibriSpeech WER, no cloud, no NPU.☆116Oct 9, 2026Updated last week
- Optimized inference for the DGX Spark and spark clusters☆120Updated this week
- qwen38-flash-next recipe for tp=2 GB10☆127Oct 6, 2026Updated last week
- Pinned one-DGX-Spark Docker recipe for DeepSeek V4 Flash with EXL3, SparkInfer, and 262K NVFP4 MLA KV cache☆166Sep 3, 2026Updated last month
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- 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
- 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
- Verified Qwen3.8 Flash-Next GGUF recipe for one NVIDIA DGX Spark or ASUS Ascent GX10☆61Updated this week
- Make your terminal string output even more beautiful 💖☆11Jul 27, 2025Updated last year
- Performance-tuned llama.cpp for AMD Strix Halo (gfx1151): FA + MoE-prefill fixes with a bundled current Mesa driver. Vulkan and HIP; port…☆216Oct 9, 2026Updated last week
- Serve Qwen3.8-Flash-Next (turboderp ExLlamaV3 pack) on one NVIDIA DGX Spark with exllamav3☆62Updated this week
- ENGRAFT: write facts into an LLM's n-gram (Engram) memory table as a removable overlay: 100 facts in a 9 MB file, no weights touched, ver…☆56Sep 30, 2026Updated 2 weeks ago
- A curated list of tools, guides, playbooks, and resources for the NVIDIA DGX Spark (GB10 Grace Blackwell personal AI supercomputer).☆86Oct 8, 2026Updated last week
- DeepSeek V4 Flash DSpark 1M NVFP4 KV recipe for 2x DGX Spark☆493Sep 10, 2026Updated last month
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Qwen3.8 27B on SGLang for DGX Spark☆474Sep 12, 2026Updated last month
- DeepSeek v4.1 Flash EXL3 2.9 bpw for 2x DGX Sparks☆274Sep 19, 2026Updated 3 weeks ago
- 🦀 Decoder-only LLM built from scratch in pure Rust using Candle — no Python, no PyTorch. Gated DeltaNet + sparse attention, fine-grained…☆110Aug 21, 2026Updated last month
- GLM-5.3-Flash EXL3 on 2x DGX Spark with TensorFold☆450Updated this week
- Simple ML Algorithm to detect licence plates☆13Nov 22, 2022Updated 3 years ago
- ☆64Sep 19, 2026Updated 3 weeks ago
- ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding☆218Aug 31, 2026Updated last month
- Google data studio connector that fetches data from api endpoint☆12Feb 26, 2021Updated 5 years ago
- Local text-to-speech: 28 voices, 10 languages, voice cloning, SDKs for Python, Swift, Go, Rust and TypeScript☆27Updated this week
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Local-first AI workbench for OCR, transcription, translation, image generation, mind maps and composable workflows. Built for DGX Spark.☆68Sep 2, 2026Updated last month
- Use a Blink security camera to shoot time-lapse images☆13Updated this week
- Qwen3.8-Flash-Next-NVFP4-vLLM-Dual-DGX-Spark☆410Sep 29, 2026Updated 2 weeks ago
- Portable optimized ROCm and Qwen3.8-27B setup for AMD Strix Halo☆83Sep 16, 2026Updated last month
- WorldPlay2: Extending Real-Time Interactive World Models in Control and Horizon☆111Oct 7, 2026Updated last week
- DeepSeek-V4-Flash-0731 on 4x CMP 170HX (sm_80): 98 tok/s decode, ~5300 tok/s prefill. DSpark speculative decoding under pipeline parallel…☆118Aug 13, 2026Updated 2 months ago
- High-performance Reticulum (RNS), built to run on any device.☆70Updated this week