---
type: "ProfilePage"
title: "myllmbox"
description: "3 recipes by myllmbox for local models, with speed, source and weights."
resource: "https://www.contextstudios.ai/local-ai/creators/myllmbox"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-10-02T20:32:13.285Z"
status: "stable"
---

# myllmbox


- [Qwen3.8-Flash-Next NVFP4 with vLLM on 2× DGX Spark (text)](https://www.contextstudios.ai/local-ai/myllmbox--qwen38-flash-next-hibrid48-2x-dgx-spark.md): 121 tok/s (Peak; Peak, 1 request, code prompt) — [source](https://github.com/myllmbox/qwen38-flash-next-cluster-recipe/blob/main/README.md)
- [Qwen3.8-Flash-Next NVFP4 with vLLM on 1× DGX Spark](https://www.contextstudios.ai/local-ai/myllmbox--qwen38-flash-next-hibrid48-1x-dgx-spark.md): 82 tok/s (Peak; Peak, 1 request, code prompt) — [source](https://github.com/myllmbox/qwen38-flash-next-recipe/blob/main/README.md)
- [MiMo-V2.6-Flash-RL 309B-A15B with vLLM on 2× DGX Spark](https://www.contextstudios.ai/local-ai/myllmbox--mimo-v26-flash-rl-2x-dgx-spark.md): 38 tok/s (Peak; Peak, 1 request, code prompt) — [source](https://github.com/myllmbox/mimo-v26-flash-cluster-recipe/blob/main/README.md)

## Related

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