Qwen3.8-Flash-Next on a Single NVIDIA DGX Spark Outscores Dual-Spark Setup in Benchmark

X postMike GannottiNews

A benchmark report from SMF Clearinghouse shows MiaAI's Qwen3.8-Flash-Next (NVFP4) scoring 87.3% on smf-bench Official A running on a single NVIDIA DGX Spark (GB10). The single-node serve outperformed the previous dual-Spark DeepSeek V4 Vision-Exp setup in overall accuracy, achieving a perfect score in coding.

Key points

  1. Qwen3.8-Flash-Next NVFP4 running on a single DGX Spark (TP=1, 262k context, MTP=3) scored 137/157 (87.3%) on smf-bench Official A with thinking disabled.
  2. In the coding category, Qwen achieved 30/30 with zero SyntaxErrors, outperforming dual-Spark DSV4 (22/30 with five syntax errors).
  3. While Qwen beat DSV4's 74.5% score on accuracy, DSV4 retained higher decode speeds (68.5 tok/s at c=1 vs. Qwen's 31.1 tok/s).
  4. Deployment stability requires empty host swap (<5 GiB) and setting KV_TARGET_GIB=16 to prevent memory watchdog failures on 128 GB UMA.

Why it matters

Running high-capability open models locally at 262k context without cloud API bills becomes increasingly practical on single-box hardware setups, provided memory parameters are carefully configured.

Analysis

Nemo's evaluation highlights a direct trade-off between inference throughput and output correctness. DSV4 remains superior for bulk throughput on two nodes, but Qwen3.8-Flash-Next on a single GB10 offers higher benchmark quality and a zero-error coding baseline suitable for agent turn workloads.

Original post

Mike Gannotti

@MichaelGannotti · 5 September 2026

Qwen3.8 Flash from @MiaAI_lab running on a single @NVIDIAAI DGX Spark crushed it this morning. Full report here t.co/zDImTHkMJi t.co/jTtMSYcdL9

37 likes0 replies17 bookmarks2.3k views

View on X

Mentioned links

Links and tools from this entry

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Article:Nemo, DGX Spark & Local Inference Engineer

    Qwen3.8-Flash-Next Scores 87.3% on a Single DGX Spark

    A local benchmark test running Qwen3.8-Flash-Next NVFP4 on a single NVIDIA DGX Spark (GB10) achieved 87.3% on smf-bench Official A, outperforming a previous dual-Spark DeepSeek V4 setup in quality.

    AI & LLMs· Research

  • X post:Mia

    Performance Update for Qwen3.8 Flash Next on DGX Spark

    Mia (@MiaAI_lab) announced a major performance update for Qwen3.8 Flash Next running on a single DGX Spark, achieving up to 108 tok/s across concurrent streams and extending the KV cache to 1M.

    520bookmarks75.7kviews

    AI & LLMs· Announcement

  • X post:Mia

    Running DeepSeek v4 Flash on a Single NVIDIA DGX Spark

    MiaAI-Lab published an open-source launcher allowing DeepSeek V4 Flash 0731 (EXL3) to run on a single NVIDIA DGX Spark node instead of requiring a multi-node setup.

    71bookmarks9.8kviews

    AI & LLMs· Tool

  • Repository:MiaAI-Lab/DeepSeek-v4-Flash-One-DGX-Spark

    Running DeepSeek-v4-Flash on a Single DGX Spark

    An open-source launcher and Docker recipe for running DeepSeek V4 Flash 0731 (EXL3) on a single NVIDIA DGX Spark with 128 GiB unified memory.

    328starsPython

    AI & LLMs· Tool

  • Article:Elite Test Engineering

    Serving DeepSeek V4 Flash on Dual DGX Spark Nodes

    A detailed technical setup report documents serving DeepSeek-V4-Flash (284B MoE) across two DGX Spark nodes powered by Grace Blackwell chips using Ray and vLLM. It highlights workarounds for unified memory monitoring, NCCL RDMA deadlocks, and CUDA graph issues, as well as a 45% speedup using native speculative decoding.

    AI & LLMs· Tutorial

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.