Tuned TP4 serving profile for DeepSeek-V4.1-Flash on 4x NVIDIA DGX Spark (SGLang, DSpark), built on the MiaAI-Lab recipe
☆89Nov 6, 2026Updated this week
Alternatives and similar repositories for DeepSeek-V4.1-Flash-4x-DGX-Spark-TP4
Users that are interested in DeepSeek-V4.1-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:
- GLM-5.3-Flash NVFP4 on 4x NVIDIA DGX Spark: vLLM TP4, DFlash2 adaptive draft, measured FP8 vs NVFP4 vs EXL3 vs SGLang☆42Sep 29, 2026Updated last month
- Full GLM-5.3 (753B, Int4-Int8Mix) on 4x NVIDIA DGX Spark, vLLM TP4☆23Oct 13, 2026Updated 3 weeks ago
- DeepSeek-V4.1-Flash on 4x DGX Spark TP4 switchless RoCE ring - SGLang production recipe, 600K context, DSpark MTP, benchmark archive☆30Oct 1, 2026Updated last month
- ☆32Nov 2, 2026Updated last week
- 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 last month
- 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.
- 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☆12Oct 25, 2026Updated 2 weeks ago
- Full GLM-5.3 (753B) served by TensorFold with tensor parallel 4 across four NVIDIA DGX Sparks: results, recipe, node settings, benches☆22Oct 13, 2026Updated 3 weeks ago
- A from-scratch CUDA inference engine for 1-6 DGX Sparks (GB10): GLM-5.3, GLM-5.3-Flash and DeepSeek-V4.1-Flash☆63Updated 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
- GLM-5.3-Flash (NVFP4) at TP=4 across 4x ASUS GX10 / GB10 - vLLM + mentat instead of Ray, 524k context, DFlash2. Minimal working recipe.☆95Updated this week
- DeepSeek-V4.1-Flash on 3-4x NVIDIA DGX Sparks☆291Oct 17, 2026Updated 3 weeks ago
- Reproducible Docker/vLLM deployment, tuning, and benchmarks for DeepSeek V4.1 Flash on a switchless three-node or four-node DGX Spark fab…☆146Updated this week
- DeepSeek-V4.1-Flash on 4x DGX Spark (GB10): exact 4-node TensorFold (Zig) recipe, vision, 1M context☆11Updated this week
- Switchless RoCE collectives, NCCL profiles and fabric tooling for DGX Spark inference recipes☆41Updated this week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- 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)…☆162Oct 26, 2026Updated last 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…☆65Updated this week
- Experimental runtime reclamation of GB10 display-reserved memory into ordinary Linux RAM, with guarded driver, local signing, and reboot …☆13Oct 23, 2026Updated 2 weeks ago
- GLM-5.3-Flash (NVFP4) at TP4 across 4x DGX Spark via a switchless RoCE ring + DFlash2 — reproducible recipe☆111Oct 25, 2026Updated 2 weeks ago
- GLM-5.3-Flash (FP8) + DFlash2 speculative decoding on 4x NVIDIA DGX Spark / ASUS GX10: vLLM TP4, 256K context, switchless ConnectX-7 ring…☆30Oct 1, 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 …☆57Oct 10, 2026Updated 3 weeks ago
- GLM-5.3-Flash NVFP4 on two or four DGX Sparks cabled as a ring, with no switch: the RiNGSiDE serving recipe☆30Sep 27, 2026Updated last month
- keys- 1M context: Inkling-Small-NVFP4 + DSpark + NVFP4 KV on SGLang, sm_121a-optimized on Two DGX Sparks — one-shot agent-executable rec…☆10Aug 17, 2026Updated 2 months ago
- Three-DGX-Spark TP3 serving recipe for GLM-5.3 Flash☆21Oct 5, 2026Updated last month
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Live dashboard: fire N parallel streaming coding-agent runs at any OpenAI-compatible endpoint — per-run TTFT/tok-s/E2E, real kill switch,…☆27Jul 23, 2026Updated 3 months ago
- DeepSeek-v4-Flash 0731 recipe for 2x DGX Sparks☆1,513Oct 4, 2026Updated last month
- First Int4-Int8Mix quantization of the full GLM-5.3 (743B), served on 4x NVIDIA DGX Spark (GB10) at TP4. Quantizer, verification gates, a…☆20Oct 6, 2026Updated last month
- GLM-5.3-Flash EXL3 on 2x DGX Spark with TensorFold☆529Updated this week
- qwen38-flash-next recipe for tp=2 GB10☆133Oct 29, 2026Updated last week
- Qwen3.8-Flash-Next-NVFP4-vLLM-Dual-DGX-Spark☆414Sep 29, 2026Updated last month
- GLM-5.3 Flash EXL3 for 2-4x DGX Sparks☆753Updated this week
- Reproducible LLM inference on four NVIDIA DGX Spark (GB10) nodes wired as a direct switchless ConnectX ring — serving profiles, ring laun…☆21Oct 30, 2026Updated last week
- 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
- 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 (abliterated EXL3) on 2x NVIDIA DGX Spark with the TensorFold engine: 1.8x faster decode than vLLM, 4x256k concurrent threa…☆122Oct 30, 2026Updated last week
- GLM-5.2 QuantTrio TP=4+DCP2 on 4x NVIDIA DGX Spark (GB10) — tuned and measured under a real agent workload. Adaptive MTP, the indexer law…☆20Aug 24, 2026Updated 2 months ago
- DeepSeek-V4-Flash-DSpark optimized vLLM 0.26.0 SM121 dual-GB10 evidence (NVFP4 KV, B12X, DSpark K6)☆31Aug 3, 2026Updated 3 months ago
- Minimal read-only OS image for GB10 (DGX Spark / ASUS GX10) boxes☆97Nov 1, 2026Updated last week
- sparkDash ⚡ — Multi-DGX Spark Monitoring Dashboard☆844Updated 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
- DeepSeek V4 Flash DSpark 1M NVFP4 KV recipe for 2x DGX Spark☆496Sep 10, 2026Updated last month