---
type: "Article"
title: "MiMo-V2.6-Pro-MOPD ARVQ/NVFP4 hybrid with vLLM on 4× DGX Spark (1M context)"
description: "MiMo-V2.6-Pro-MOPD ARVQ/NVFP4 hybrid with vLLM on 4× DGX Spark (1M context): recipe by drowzeys with speed, condition and source for every number, weights and license."
resource: "https://www.contextstudios.ai/local-ai/drowzeys--mimo-v26-pro-mopd-arvq-hybrid21-4spark"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-11-11T03:30:05.737Z"
status: "stable"
---

# MiMo-V2.6-Pro-MOPD ARVQ/NVFP4 hybrid with vLLM on 4× DGX Spark (1M context)

MiMo-V2.6-Pro-MOPD ARVQ/NVFP4 hybrid with vLLM on 4× DGX Spark (1M context): 24.2 tok/s according to github.com (dataset as of Nov 3, 2026).

- Creator: [drowzeys](https://www.contextstudios.ai/local-ai/creators/drowzeys.md)
- Engine: vLLM-Fork jarrelscy/vllm-mimo-v26-arvq-sm120 (Image ghcr.io/drowzeys/mimo-v26-pro-arvq-spark:63430f7-sm121-v4)
- Quantization: Jarrelscy ARVQ/NVFP4-Hybrid (hybrid-21: 21% NVFP4-Hot-Experten), BF16 KV
- Model family: MiMo-V2.6-Pro
- Hardware: dgx-spark x4
- Context: 1048576

## All numbers

- 24.2 tok/s (Everyday; Everyday, 1 request, prose prompt, with MTP k=2 (per recipe)) — [source](https://github.com/drowzeys/keys-MiMo-V2.6-Pro-MOPD-C3-Jarrelscy-ARVQ-4-DGX-Sparks-1M-Context#speed-live-mopd-c3-image-v4-2026-09-28)
- decode_tps: 24.2 (1 request) — [source](https://github.com/drowzeys/keys-MiMo-V2.6-Pro-MOPD-C3-Jarrelscy-ARVQ-4-DGX-Sparks-1M-Context#speed-live-mopd-c3-image-v4-2026-09-28)
- decode_tps: 46.3 (4 parallel requests) — [source](https://github.com/drowzeys/keys-MiMo-V2.6-Pro-MOPD-C3-Jarrelscy-ARVQ-4-DGX-Sparks-1M-Context#speed-live-mopd-c3-image-v4-2026-09-28)
- prefill_tps: 1074 (1 request) — [source](https://github.com/drowzeys/keys-MiMo-V2.6-Pro-MOPD-C3-Jarrelscy-ARVQ-4-DGX-Sparks-1M-Context#speed-live-mopd-c3-image-v4-2026-09-28)

## Weights

- [drowzeys/keys-MiMo-V2.6-Pro-MOPD-Jarrelscy-ARVQ-hybrid21](https://huggingface.co/drowzeys/keys-MiMo-V2.6-Pro-MOPD-Jarrelscy-ARVQ-hybrid21) (main, mit)
- [XiaomiMiMo/MiMo-V2.6-Pro-MOPD](https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-MOPD) (base, mit)
- [jarrelscy/MiMo-V2.6-Pro-RL-ARVQ-hybrid](https://huggingface.co/jarrelscy/MiMo-V2.6-Pro-RL-ARVQ-hybrid) (other, mit)

[https://github.com/drowzeys/keys-MiMo-V2.6-Pro-MOPD-C3-Jarrelscy-ARVQ-4-DGX-Sparks-1M-Context](https://github.com/drowzeys/keys-MiMo-V2.6-Pro-MOPD-C3-Jarrelscy-ARVQ-4-DGX-Sparks-1M-Context)

## Related

- [Local AI on your hardware.](https://www.contextstudios.ai/local-ai.md)
