X postMiaAnnouncement
High-throughput serving of long-context multimodal models on accessible hardware is critical for real-world deployments, and speculative decoding methods are key to improving inference speeds.
The post highlights benchmarks for Inkling-Small at a 1M context length on dual DGX Spark systems using SGLang. The author specifically contrasts Inkling-Small with DeepSeek V4 Flash by pointing out its multimodal capabilities spanning images, audio, and video alongside text.
Mia
@MiaAI_lab · 2 August 2026
Run Inkling-Small on 2x @NVIDIAAI DGX Spark with 1M context ✨ - SGLang with dspark speculative drafts ~34 tok/s (single stream) ~79 tok/s (6 concurrent sessions) Unlike DeepSeek V4 Flash which supports only text, Inkling-Small also supports images, audio, and video. Special
129 likes13 replies106 bookmarks9.5k views
View on XSummary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.
Similar in content, found by the AI search.
X post:Mia
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
Repository:MiaAI-Lab/DeepSeek-v4-Flash-One-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
Article:Elite Test Engineering
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.
X post:Mia
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
X post:Mike Gannotti
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.
17bookmarks2.3kviews
VideoVideo:EliteTestEngineering
EliteTestEngineering demonstrates running DeepSeek V4 Flash across a two-node cluster consisting of a DGX Spark and an Acer GN100. The MoE model achieves inference speeds of 10 to 16.5 tokens per second but quickly encounters memory limitations with longer context windows.
Parts of this content were created with the assistance of AI.
