SparkLab running frontier models on NVIDIA DGX Spark

Built for NVIDIA DGX Spark (GB10)

SparkLab

Documentation Latest release Apache License 2.0

Oakmind AI on X Oakmind AI on Hugging Face

Run frontier open-weight models privately on NVIDIA DGX Spark.

SparkLab is developed by SixteenMiles Labs, a research lab under Oakmind AI.

SparkLab is a GB10-native inference product for local, single-system deployments. It combines immutable model recipes, unified-memory admission, resumable checkpoint acquisition, FTW preparation, NVMe-backed MoE execution, and OpenAI- and Anthropic-compatible APIs.

Supported production target

SparkLab deliberately supports one narrow hardware profile:

  • NVIDIA GB10 Grace Blackwell Superchip (SM121)
  • 128 GB coherent unified memory
  • ARM64 Linux or DGX OS
  • NVIDIA driver r580 or newer and CUDA 13 toolkit
  • Local NVMe storage for checkpoints, FTW artifacts, and disk-backed experts
  • One local DGX Spark; multi-node and high-concurrency serving are outside the Beta scope

Platform, memory, swap, dependency, and storage requirements fail closed before a recipe launch. Unsupported hardware may still work through native runtime fallbacks, but it is not a SparkLab support claim.

Why SparkLab

  • GB10 admission: sparklab doctor validates architecture, CUDA, unified memory, swap, dependencies, NVMe backing, and free capacity with human and JSON output.
  • Immutable recipes: acquisition pins model revisions, records manifests, validates prepared artifacts, and rejects mismatched provenance.
  • Unified-memory planning: runtime admission budgets weights, expert cache, KV and recurrent state, workspaces, and an operating-system reserve without counting swap as capacity.
  • Frontier models beyond memory: FTW expert banks and bounded NVMe-backed caching let selected MoE checkpoints exceed physical memory.
  • Stable local APIs: OpenAI Chat Completions, Responses, and Anthropic Messages share one loopback endpoint with streaming, reasoning, and tool-call support.
  • Evidence-bound claims: model status and performance point to versioned, complete-checkpoint GB10 records rather than inferred capability.

Model portfolio

Model Parameters Quantization Status tok/s TTFT(s) Run
Fast — routine chat, editing, and short agent loops
Qwen3.6-35B-A3B 35B total / 3B active NVFP4 · FTW Certified 67.79 0.329 Instructions
Frontier — quality-first coding, reasoning, and long agent work
Qwen3.8-Flash-Next 125B LM + 55B auxiliary / 6B active NVFP4 · FTW Experimental 16.61 0.403 Instructions
DeepSeek V4 Flash 284B total / 13B active DS-FP4 Preview 10.28 0.604 Instructions
GLM-5.3 Flash 320B total / 18B active NVFP4 + KDA FP8 · FTW Experimental 6.27 5.681 Instructions
Research — bounded execution outside the interactive envelope
GLM-5.2 753B total / 40B active NVFP4 Experimental 0.80 2.570 Instructions
GLM-5.3 753B total / 40B active NVFP4 + resident FP8 · FTW Experimental 0.81 2.530 Instructions
Kimi K3 2.8T total / 16 of 896 experts ModelOpt NVFP4/FP8 · FTW Experimental 0.16 395.405 Instructions

Status meanings:

  • Experimental: implementation or measured evidence exists, but required gates remain incomplete or failed.
  • Preview: a bounded supported path exists, but the full release promise is incomplete.
  • Certified: the exact recipe, revision, artifact, and release environment passed all required correctness, parser, agent, context, latency, memory, NVMe, and endurance gates.

Run sparklab models --json for exact recipe versions, checkpoint revisions, artifact fingerprints, implementation state, evidence IDs, and known constraints.

Documentation

Contribution

SparkLab is stewarded in public by SixteenMiles Labs. Oakmind AI provides organizational backing, legal stewardship, and commercial support.

Credits and citation

SparkLab incorporates source and research contributions from FreeToken and builds on open inference projects including mini-sglang, SGLang, vLLM, FlashInfer, flash-linear-attention, LightLLM, and llama.cpp.

If you use SparkLab, cite the software:

@software{sixteenmileslabs2026sparklab,
  title={SparkLab: Frontier Open-Weight Model Inference on NVIDIA DGX Spark},
  author={{SixteenMiles Labs}},
  year={2026},
  url={https://github.com/sixteen-miles-labs/sparklab},
  license={Apache-2.0}
}

For work that builds on SparkLab's FreeToken-derived execution techniques, also cite the FreeToken paper:

@article{yang2026freetoken,
  title={FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution},
  author={Yang, Shuo and Fan, Xiaoze and Pan, Melissa and Xi, Haocheng and Wang, Zhe and Sun, Shanlin and Keutzer, Kurt and Han, Song and Zaharia, Matei and Xu, Chenfeng and Stoica, Ion},
  journal={arXiv preprint arXiv:2608.16157},
  year={2026}
}

Project links

Data verified by PyPI on Aug 31, 2026
Data provided by the project maintainers, verified at the time the release was uploaded to PyPI.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Newer release available (0.1.2)

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for lidaiqing from gravatar.com lidaiqing

Credits

Author/Maintainer: SixteenMiles Labs

GitHub Statistics

Data verified by PyPI on Aug 31, 2026
The GitHub source repository was provided by the project maintainers and verified by PyPI at the time of upload. Stars, forks, and open issues/PRs are derived from that repository and have not been independently verified.

License expression

Apache-2.0
View SPDX License List

Requires

Python >=3.10

Provides Extra

dev fi sgl accel

Tags

ai dgx-spark gb10 inference moe sparklab

Classifiers

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

sparklab-0.1.1-cp313-cp313-manylinux_2_27_aarch64.whl (1.4 MB view details)

Uploaded CPython 3.13manylinux: glibc 2.27+ ARM64

sparklab-0.1.1-cp312-cp312-manylinux_2_27_aarch64.whl (1.4 MB view details)

Uploaded CPython 3.12manylinux: glibc 2.27+ ARM64

sparklab-0.1.1-cp311-cp311-manylinux_2_27_aarch64.whl (1.4 MB view details)

Uploaded CPython 3.11manylinux: glibc 2.27+ ARM64

sparklab-0.1.1-cp310-cp310-manylinux_2_27_aarch64.whl (1.4 MB view details)

Uploaded CPython 3.10manylinux: glibc 2.27+ ARM64

File details

Details for the file sparklab-0.1.1-cp313-cp313-manylinux_2_27_aarch64.whl.

File metadata

File hashes

Hashes for sparklab-0.1.1-cp313-cp313-manylinux_2_27_aarch64.whl
Algorithm Hash digest
SHA256 2b8231fabe1b8c0e0436a6f9bc416020b708fdcdcf1b15797a5fd3336f27ee95
MD5 201de8d3dde09ecba3b3ad978d0c61f2
BLAKE2b-256 c894114cb5aa32c7a6eefff9bcdad65e95e9b9e4bf502eb5afe9734fcb9b1e2f

See more details on using hashes here.

Provenance

The following attestation bundles were made for sparklab-0.1.1-cp313-cp313-manylinux_2_27_aarch64.whl:

Publisher: release.yml on sixteen-miles-labs/sparklab

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file sparklab-0.1.1-cp312-cp312-manylinux_2_27_aarch64.whl.

File metadata

File hashes

Hashes for sparklab-0.1.1-cp312-cp312-manylinux_2_27_aarch64.whl
Algorithm Hash digest
SHA256 aeec7e432af4bcc3a9e5b45b8b84d9aa0f095d07d0be03839d4d1f59a4a04a10
MD5 2331cc572957f6112ff7be0960b275d5
BLAKE2b-256 b18b723a1f88af8a56345c99b883a3ef79d299b69a8c530ac43931b2f827cbfe

See more details on using hashes here.

Provenance

The following attestation bundles were made for sparklab-0.1.1-cp312-cp312-manylinux_2_27_aarch64.whl:

Publisher: release.yml on sixteen-miles-labs/sparklab

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file sparklab-0.1.1-cp311-cp311-manylinux_2_27_aarch64.whl.

File metadata

File hashes

Hashes for sparklab-0.1.1-cp311-cp311-manylinux_2_27_aarch64.whl
Algorithm Hash digest
SHA256 be4c1121fb9092663dad025fcb64ef34d8ecb295ace380ac6bc80ac47f57f25b
MD5 557f1726795f8a4e96a0aa15c171cb89
BLAKE2b-256 ee433fb4d5d68f1e7e608dfa36ecf0048b70803fd0671e2b7492184245800d09

See more details on using hashes here.

Provenance

The following attestation bundles were made for sparklab-0.1.1-cp311-cp311-manylinux_2_27_aarch64.whl:

Publisher: release.yml on sixteen-miles-labs/sparklab

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file sparklab-0.1.1-cp310-cp310-manylinux_2_27_aarch64.whl.

File metadata

File hashes

Hashes for sparklab-0.1.1-cp310-cp310-manylinux_2_27_aarch64.whl
Algorithm Hash digest
SHA256 b7f259538b4a22ade315a4e0e4e467d6a952227cf0da6f704d05b6d4c1959b35
MD5 675e4d31b5e70728d7f38efe4124f999
BLAKE2b-256 dbabb52746dd34638989f5b7aa48a27a663d13a23f580ee615e5c35cc558f766

See more details on using hashes here.

Provenance

The following attestation bundles were made for sparklab-0.1.1-cp310-cp310-manylinux_2_27_aarch64.whl:

Publisher: release.yml on sixteen-miles-labs/sparklab

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

0.1.2

4 files

This release

0.1.1 This release

4 files

0.1.0

4 files

Pre-release

0.1.0b2

4 files

Pre-release

0.1.0b1

4 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page