DGX Spark/Guides/Best models for DGX Spark
Buying analysis · October 2026 edition

Best models for DGX Spark, October 2026 edition

By Samuel Seidel · Published September 9, 2026 · Updated 24 October 2026

On one DGX Spark, Qwen3.6-35B-A3B in NVFP4 with an MTP draft is the fastest current pick, reported at 86.3 tok/s single-stream at a 4k context fill. On two Sparks, DeepSeek-V4-Flash runs its official FP8 weights at about 44 tok/s. The tables below give one pick per use case, with the quantization, engine, source and date behind each number. Every figure is reported by a third party unless it says GPUwerk-measured. Sources read 24 October 2026.

Verdict: 1 Spark

Use case Model Quant Engine Single-stream tok/s Source Date
Fastest chat and agentsQwen3.6-35B-A3BNVFP4 + MTP (3-token draft)vLLM, eugr build86.3 at 4k fill (advantage)SparkBench2026-08-04
Coding, GPUwerk-measuredQwen3-Coder-30B-A3BAWQ 4-bitvLLM 0.27.180.9GPUwerk benchmarks2026-09-02
Small and efficientNemotron 3 Nano 30B-A3BNVFP4 (W4A16)vLLM 0.20.1, patched74.75ai-muninn2026-05-01
General and visionGemma 4 26B-A4BNVFP4 + MTPvLLM 0.26.1 nightly54.9NVIDIA forum2026-08-10
Dense 27BQwen3.8-27BNVFP4 + DFlash2 (8-token draft)SGLang38.1 at 4k fillSparkBench2026-09-10
Dense 27B, older releaseQwen3.6-27BNVFP4not stated33noze, citing MiaAI-Lab2026-08-06
Batch and agent fleetsgpt-oss-120bMXFP4vLLM 26.03 container33.5 (862.8 aggregate at 256)Dendro Logic2026-04-22
Largest model, cut to fitDeepSeek-V4-Flash2-bitds4 fork for GB10~28NVIDIA forum2026-08-01
GLM on one boxGLM-5.3-Flash (320B-A18B)UD-Q2_K_XL, 108.72 GBllama.cpp build 1067715.4 prose / 23.6 codeai-muninn2026-08-30

SparkBench figures are decode after a fixed context fill. Qwen3.6-35B-A3B drops to 78.8 tok/s at 50k and 31.5 at 100k, and Qwen3.8-27B to 19.1 at 50k. Other one-Spark reports for Qwen3.6-35B-A3B are 81 tok/s (NVFP4, noze, citing MiaAI-Lab) and ~106 tok/s with an Unsloth speculative-decoding recipe (openclawdc). Nemotron 3 Nano is also reported at ~67 tok/s on an earlier community vLLM image (NVIDIA forum). DeepSeek-V4-Flash on one Spark is reported from ~13 tok/s (patched vLLM fork, prose) to ~55 typical (reduced NVFP4, openclawdc). Speculative decoding drafts several tokens per weight read, so its gain depends on how predictable your text is.

Verdict: 2 Sparks

Use case Model Quant Engine Single-stream tok/s Source Date
Frontier MoE, official weightsDeepSeek-V4-Flash (284B, 13B active)official FP8 + MTPvLLM (jasl fork), TP=2~44 (advantage)NVIDIA forum2026-05-16
Very long contextDeepSeek-V4-Flashofficial checkpoint, FP8 KV, 1M contextvLLM 0.21.1, TP=245.7 empty, 30.4 at 980KNVIDIA forum2026-06-04
GLM-5.xGLM-5.22-bit experts, 96K contextTP=2, engine not named~25.8openclawdc2026-08-05
235B MoE at 4-bitQwen3-235B-A22BUD-Q4_K_XL, 134 GBllama.cpp RPC~12.5 (about 1.8 on one Spark)NVIDIA forum2025-12-17

The vLLM recipe for DeepSeek-V4-Flash (updated 29 September 2026) uses two GB10 nodes with TP=2 and says the checkpoint does not fit one Spark’s 128 GB. GPUwerk has not run this model on two nodes; its one two-node run is a dense 32B model. Two cabled Sparks rent as a cluster for $1.79/hour; one Spark is $0.79/hour. The two-node cluster guide covers the setup.

Chat, single person

Pick a mixture-of-experts model with about 3B active parameters. Qwen3.6-35B-A3B at 86.3 tok/s and Qwen3-Coder-30B-A3B at 80.9 tok/s are both far above the roughly 10 tok/s line GPUwerk’s benchmarks page draws for a usable chat window. gpt-oss-120b is the larger option at 58.7 tok/s on llama.cpp build 7941 (llama.cpp DGX Spark results). Dense models are slow here: Nemotron Super 49B is at 5.79 tok/s and Llama 3.3 70B at 6.0.

Coding

Qwen3-Coder-30B-A3B is the coding pick GPUwerk has measured: 80.9 tok/s single-user and 5,705 tok/s prefill on an 8,192-token prompt, so a large file or diff as context is handled quickly. Qwen3.6-35B-A3B is faster in the reported runs. Qwen3.8-27B is the dense alternative if you want its quality and can accept 38 tok/s at short context.

Batch and agent-fleet work

Here aggregate throughput matters more than single-stream speed. gpt-oss-120b reaches 862.8 tok/s aggregate at 256 concurrent under vLLM. Nemotron Super 49B is slow for one user but reaches 695.1 tok/s at the same concurrency. GPUwerk measured Qwen3-Coder-30B-A3B at 3,235 tok/s total throughput at 256. Llama 3.3 70B peaks at 485 tok/s at 128 concurrent, then falls to 300 at 256, so keep batch jobs on it near 128.

Long prompts, short answers

Nemotron-3-Super-120B-A12B at NVFP4 decodes at 22.7 to 23.7 tok/s and prefills near 1,900 tok/s, which suits contract review and extraction work. It runs on stock vLLM without a fork. Decode at 4k, 50k and 100k tokens for the models above is compiled in DGX Spark long-context performance, and the newest large MoE releases across 2 to 8 Sparks in large MoE models on multiple Sparks.

When one Spark is not enough

Active parameters set speed on this hardware, and total parameters set fit. DeepSeek-V4-Flash has only 13B active, so it is fast enough, but its 284B total does not fit one Spark at the official precision. On one Spark it needs 2-bit or reduced builds, which sit below the 4-bit level where quality starts to drop on most models. A second Spark runs the official weights instead. Dense models past 30 to 50B hit the 273 GB/s bandwidth ceiling explained in the glossary, and a second Spark does not fix that for a single user.

How to pick

Start from the job. One person typing prompts: Qwen3.6-35B-A3B or Qwen3-Coder-30B-A3B. Many users or an agent fleet: gpt-oss-120b or Nemotron Super 49B, sized to your concurrency. Long documents with short answers: Nemotron-3-Super-120B. The official DeepSeek-V4-Flash weights: two Sparks.

Before you trust any number here, rent a DGX Spark at $0.79/hour, or two at $1.79/hour, billed per minute, and run your own prompts. A first engagement covers picking and tuning a model for a specific workload if you would rather hand that off.

FAQ

What is the best DGX Spark model for chat?

On one Spark, Qwen3.6-35B-A3B in NVFP4 with an MTP draft is the fastest current pick: SparkBench reports 86.3 tok/s single-stream at a 4k context fill (vLLM, 4 August 2026). Qwen3-Coder-30B-A3B is the fastest model GPUwerk has measured itself, at 80.9 tok/s on vLLM 0.27.1.

What is the best DGX Spark model for coding?

Qwen3.6-35B-A3B for speed on one Spark (86.3 tok/s reported at 4k). Qwen3-Coder-30B-A3B is the coding-tuned model GPUwerk measured at 80.9 tok/s, and it reached 3,235 tok/s total throughput at 256 concurrent requests. For a dense model, Qwen3.8-27B is reported at 38.1 tok/s at 4k with NVFP4 and speculative decoding on SGLang.

What does a second DGX Spark let me run?

Models whose official weights do not fit in 128 GB. DeepSeek-V4-Flash runs its official FP8 checkpoint on two Sparks with vLLM and TP=2 at about 44 tok/s single-stream (NVIDIA forum, May 2026). GPUwerk rents two cabled Sparks as a cluster for $1.79/hour.

First top-up: pay $20, get $30 in credit

Stop reading model pages. Run one.

A dedicated Spark from $0.79/h, billed by the minute, with Qwen3-Coder-30B-A3B and Llama 3.3 70B staged by default.

Create account Browse all models