Best Models to Run on NVIDIA DGX Spark (August 2026): 1, 2, 3 & 4-Spark Setups

Bottom Line (August 2026)

• 1 Spark — Qwen 3.6 35B-A3B NVFP4 for speed (~106 tok/s at 256K context) or DeepSeek V4 Flash NVFP4 for the best coding quality that fits (~55 tok/s typical).
• 2 Sparks — the sweet spot. DeepSeek V4 Flash DSpark at the full 1M context (~42 tok/s at 1M, 44–63 tok/s at working contexts). Omni options: Inkling-Small and MiMo-V2.5.
• 3 Sparks — GLM-5.2 NVFP4+AQLM (~380K context) with the community vision build, or DeepSeek V4 Flash on two units + a free Spark for ComfyUI and small models.
• 4 Sparks — unpruned GLM-5.2 (744B) at up to 1M context, ~42 tok/s peak. The strongest local intelligence on a desk, for about $16k of hardware.

All numbers below are single-stream decode rates from community recipes and NVIDIA forum reports, mostly via vLLM with NVFP4 quantization. Batch throughput is much higher — the Spark’s real advantage over a Mac shows up under concurrency.

The Hardware, Briefly

One DGX Spark is a GB10 Grace Blackwell chip with 128GB of unified LPDDR5X at ~273 GB/s. That bandwidth is the constraint: dense 70B-class models decode slowly. The winners on this box are MoE models with small active parameter counts (3B–15B active) quantized to NVFP4 — Blackwell’s native 4-bit floating-point format, which keeps quality close to FP8 at half the memory.

The second thing that defines the platform: each Spark has a 200 Gb/s ConnectX QSFP port. Two units connect back-to-back with one cable and run tensor-parallel as a 256GB machine. Three and four-unit RoCE clusters are now routine in the community. No Mac can do this.

1× DGX Spark (128GB)

Our pick: Qwen 3.6 35B-A3B NVFP4. At ~106 tok/s with the full 256K window it is faster than most cloud APIs feel, and it is the best agentic driver for OpenClaw at this tier. Run DeepSeek V4 Flash instead when coding quality matters more than speed — it is the same model family that tops SWE-bench among open weights, squeezed into 128GB at NVFP4 with a trimmed context.

Watch item: Qwen 3.8 27B is expected shortly and may reshuffle this table.

2× DGX Sparks (256GB) — The Sweet Spot

Our pick: the DeepSeek V4 Flash DSpark checkpoint. This is a purpose-built recipe — FP4 experts plus an NVFP4 MLA KV cache — that holds the entire 1M-token context in memory across two Sparks with tensor parallelism. Practical notes from the recipe threads: MTP speculative decode is what gets you into the 55–63 tok/s range on code, and the current patch level matters (without it you get roughly half speed at unchanged quality).

If you want one setup that also sees and hears, run MiMo-V2.5 Omni or Inkling-Small instead — both hold 1M context at NVFP4 KV on two Sparks, something no single consumer box can do with an omnimodal model.

3× DGX Sparks (384GB)

Two good patterns:

1. GLM-5.2 NVFP4+AQLM across all three — ~380K context with MTP serving, and a community vision-enabled build (a small trained projector maps a frozen vision tower into GLM’s token space; the text backbone is byte-identical to upstream). This is the strongest intelligence-per-desk before you go to four units. MiMo-V2.5 Omni also scales to TP=3 at 1M context, ~39 tok/s.
2. DeepSeek V4 Flash on two units + the third Spark free for ComfyUI, image models, embeddings, and small agent models. You keep DSpark coding speeds and gain a dedicated media/agent box. For an OpenClaw multi-agent setup this is the configuration we would run.

4× DGX Sparks (512GB)

Unpruned GLM-5.2 — 744B total / ~40B active — at up to 1M context. The 4x recipe (NVFP4 compact KV at 58% the size of FP8, sparse MLA, MTP-5 speculative decode) reports ~42 tok/s peak decode, ~30 tok/s at 64K context, ~819 tok/s prefill — with no pruning, unlike earlier 4x attempts. That is a frontier-class model, fully private, on roughly $16k of hardware drawing less power than one space heater.

The alternative at 4 units is DeepSeek V4 Flash on two Sparks plus any 2x setup on the other pair — for example an omni model, or a dedicated image/video pipeline.

Spark vs Mac Studio at This Money

The honest comparison, since both live at the 128GB tier:

• Mac Studio M4 Max 128GB has ~2x the memory bandwidth (546 vs ~273 GB/s) — dense models decode faster, and it is quieter and simpler. See Best Local LLMs for 128GB RAM.
• DGX Spark wins on CUDA (NVFP4, vLLM, TensorRT, ComfyUI), on batch/concurrent throughput, and — decisively — on clustering. There is no path from one Mac Studio to a 512GB tensor-parallel machine. There is from one Spark.

Buy the Mac if you will only ever run one box. Buy the Spark if the 2x sweet spot or the 4x GLM-5.2 endgame is where you are headed.

See Also

• Best Local LLMs for 128GB RAM — the Mac-side view of this memory tier
• Best Local LLM by GPU (hub) — per-GPU picks
• Best Local LLM for RTX 5090 — the 32GB VRAM alternative
• Mac Studio vs RTX Workstation for Local LLMs — the broader platform question
• Why Is My Local LLM So Slow? — bandwidth math explained
• Best Local Models for OpenClaw — model-first guide