DeepSeek V4.1 Flash 1017 runs on a single 128GB DGX Spark at 39.4 tok/s
A ~114GB VQ build served DeepSeek V4.1 Flash 1017 on one DGX Spark at 39.4 tok/s decode and ~1,145 tok/s prefill with a 110K prompt; Artificial Analysis rose 39 to 45 and cost per task fell $0.49 to $0.26.
So a few days ago I said DeepSeek V4.1 Flash 1017 had been squeezed from a ~510GB checkpoint → ~114GB, specifically targeting a single 128GB DGX Spark… …but nobody had actually benchmarked it on the Spark yet. Now they have. 👀 One DGX Spark: 🧠 DeepSeek V4.1 Flash 1017 💾 ~114GB VQ build 🖥️ 111–113GB memory used 💿 203GB Engram tables streamed from SSD ⚡ 39.4 tps weighted decode 🚀 ~1,145 tps prefill @ ~32K 📚 tested with a 110K-token prompt So yeah, a single 128GB Spark is actually serving it. Meanwhile, the independent scores are in. Artificial Analysis: Previous V4.1 Flash → 39 New 1017 → 45 🚀 That's +6 points and puts it equal #2 among open-weight models on their Intelligence Index. AA also measured: 💰 cost/task → $0.49 → $0.26 ⚠️ The Spark build is an aggressive ~1.6-bit VQ, so this is not full-checkpoint quality.
This post quotes another post: x.com/teksedge/status/2111547801620394454