---
type: "Article"
title: "Qwen3.8-2.4T-A95B UD-Q1_0 with llama.cpp on 4× DGX Spark"
description: "Qwen3.8-2.4T-A95B UD-Q1_0 with llama.cpp on 4× DGX Spark: recipe by Weschera with speed, condition and source for every number, weights and license."
resource: "https://www.contextstudios.ai/local-ai/weschera--qwen38-24t-a95b-ud-q1_0-mtp3-4x-dgx-spark"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-10-02T22:01:46.423Z"
status: "stable"
---

# Qwen3.8-2.4T-A95B UD-Q1_0 with llama.cpp on 4× DGX Spark

Qwen3.8-2.4T-A95B UD-Q1_0 with llama.cpp on 4× DGX Spark: 7.76 tok/s according to github.com (dataset as of Sep 29, 2026).

- Creator: [Weschera](https://www.contextstudios.ai/local-ai/creators/weschera.md)
- Engine: llama.cpp
- Quantization: Unsloth UD-Q1_0 GGUF (1-bit dynamic, 397,256,393,248 bytes, 10 Shards); MODEL_SHA256SUMS im Repo
- Model family: Qwen3.8-2.4T-A95B
- Hardware: dgx-spark x4
- Context: 65536

## All numbers

- 7.76 tok/s (Peak; Peak, 1 request, best value reported by source, prompt 121 tokens) — [source](https://github.com/Weschera/Qwen3.8-2.4T-A95B-UD-Q1_0-4x-DGX-Spark/blob/main/README.md)
- decode_tps: 7.76 (1 request) — [source](https://github.com/Weschera/Qwen3.8-2.4T-A95B-UD-Q1_0-4x-DGX-Spark/blob/main/README.md)

## Weights

- [unsloth/Qwen3.8-2.4T-A95B-GGUF](https://huggingface.co/unsloth/Qwen3.8-2.4T-A95B-GGUF) (main, other)

[https://github.com/Weschera/Qwen3.8-2.4T-A95B-UD-Q1_0-4x-DGX-Spark](https://github.com/Weschera/Qwen3.8-2.4T-A95B-UD-Q1_0-4x-DGX-Spark)

## Related

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