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-vocab MTP draft; TP2 SPEED 53.7; TP4 CONTEXT 9M KV pool. Launchers, patch, 40-prompt harness, KV ledger, credits. SGLang TP2 day-0 lane kept.
☆138Sep 7, 2026Updated 2 months ago
Alternatives and similar repositories for Qwen3.8-Flash-Next-NVFP4-DGX-Spark
Users that are interested in Qwen3.8-Flash-Next-NVFP4-DGX-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:
- 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…☆245Sep 30, 2026Updated last month
- 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
- Qwen3.8-Flash-Next-NVFP4-vLLM-Dual-DGX-Spark☆419Sep 29, 2026Updated last month
- Serve LibertAIDAI/GLM-5.3-Flash-NVFP4 on 2x NVIDIA DGX Spark (GB10) with patched vLLM TP=2, 262k context, MTP-4.☆21Nov 2, 2026Updated 2 weeks ago
- Serve Qwen3.8-Flash-Next (turboderp ExLlamaV3 pack) on one NVIDIA DGX Spark with exllamav3☆65Oct 14, 2026Updated last month
- 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.
- GLM-5.3 Flash EXL3 for 2-4x DGX Sparks☆762Nov 4, 2026Updated 2 weeks ago
- Local image generation and editing for NVIDIA DGX Spark, powered by Qwen-Image-2.1 and Gradio.☆34Sep 21, 2026Updated last month
- 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
- qwen38-flash-next recipe for tp=2 GB10☆135Oct 29, 2026Updated 3 weeks ago
- Qwen 3.8 Flash NVFP4 with PLE NVFP4 quantized to run on a single DGX Spark☆15Aug 28, 2026Updated 2 months ago
- An GB10-optimized inference engine☆138Updated this week
- recipe for running Qwen3.8-Flash-Next on a single DGX Spark☆535Updated 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…☆65Nov 4, 2026Updated 2 weeks ago
- Pinned stock Qwen3.8-27B NVFP4 + DFlash2 recipe and measured evidence for one NVIDIA DGX Spark☆21Nov 11, 2026Updated last 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-V4.1-Flash-1017 EXL3 on 2x DGX Sparks with TensorFold☆13Nov 4, 2026Updated 2 weeks ago
- Qwen3.8-27B on one DGX Spark: SGLang + DFlash2 recipe, engine image, benchmarks, data and charts. By @redp314☆38Sep 6, 2026Updated 2 months ago
- A front door to community tools that extend the DeepSeek Harness (dsh): web access, vision, and more. Unofficial community project.☆42Sep 28, 2026Updated last month
- DeepSeek V4 Flash DSpark 1M NVFP4 KV recipe for 2x DGX Spark☆499Sep 10, 2026Updated 2 months ago
- DeepSeek-v4-Flash 0731 recipe for 2x DGX Sparks☆1,519Oct 4, 2026Updated last month
- 1 spark glm 5.3 flash☆11Sep 7, 2026Updated 2 months ago
- sparkDash ⚡ — Multi-DGX Spark Monitoring Dashboard☆905Updated this week
- Qwen3.8-Flash-Next on ONE DGX Spark (TP=1)☆641Oct 4, 2026Updated last month
- DeepSeek-V4.1-Flash-1017 on NVIDIA DGX Sparks with TensorFold + EXL3: TP4 (4 Sparks, 93.6 tok/s, 1M context) and TP2 (2 Sparks, 73 tok/s)…☆166Oct 26, 2026Updated 3 weeks ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- GLM-5.3-Flash (abliterated EXL3) on 2x NVIDIA DGX Spark with the TensorFold engine: 1.8x faster decode than vLLM, 4x256k concurrent threa…☆126Oct 30, 2026Updated 2 weeks ago
- Tuned TP4 serving profile for DeepSeek-V4.1-Flash on 4x NVIDIA DGX Spark (SGLang, DSpark), built on the MiaAI-Lab recipe☆99Updated this week
- GLM-5.3-Flash NVFP4 on two or four DGX Sparks cabled as a ring, with no switch: the RiNGSiDE serving recipe☆31Sep 27, 2026Updated last month
- Qwen3.8 27B on SGLang for DGX Spark☆484Sep 12, 2026Updated 2 months ago
- Run Qwen3.8-Flash-Next (180B) on a single DGX Spark by keeping its 51B n-gram embedding table on NVMe☆125Aug 30, 2026Updated 2 months ago
- Custom inference recipes for NVIDIA DGX Spark — Qwen 122B DFlash hybrid☆95Nov 3, 2026Updated 2 weeks ago
- qwen38-flash-next recipe for solo GB10☆176Oct 30, 2026Updated 2 weeks ago
- Reproducible Docker deployment for Qwen3.8-27B NVFP4 on NVIDIA DGX Spark (GB10, SM121) via OpenAI-compatible vLLM. Known-good baseline + …☆12Aug 14, 2026Updated 3 months ago
- Full GLM-5.3 on 4x DGX Spark with kindlingai gr8 (TP4): RigMark prose c1 29.0 -> 40.6 tok/s (+40 %), c4 63.7 -> 76.6☆14Oct 25, 2026Updated 3 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.
- 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
- 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 2 weeks ago
- Mixed-capability LLM benchmark for DGX Spark — 57 scenarios, 10 domains, partial-credit grading, trial statistics☆171Oct 13, 2026Updated last month
- 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 …☆58Oct 10, 2026Updated last month
- GLM-5.2 on 4x DGX Spark with adaptive MTP K2/K4/K5, FULL CUDA graphs, DCP2, 520K context, and a downloadable ARM64 runtime image.☆13Aug 8, 2026Updated 3 months ago
- ☆12Aug 31, 2026Updated 2 months ago
- Userland fan control for NVIDIA DGX Spark, with additive RPM floors, a temperature-based curve, Secure Boot signing, and DKMS support.☆54Oct 29, 2026Updated 2 weeks ago
Are these results useful?