---
type: "Article"
title: "DeepSeek-V4.1-Flash-1017 EXL3 2.9 bpw with TensorFold on 2× DGX Spark"
description: "DeepSeek-V4.1-Flash-1017 EXL3 2.9 bpw with TensorFold on 2× DGX Spark: recipe by tonyd2wild with speed, condition and source for every number, weights and license."
resource: "https://www.contextstudios.ai/local-ai/tonyd2wild--deepseek-v4.1-flash-1017-tensorfold-exl3-2.9bpw-2x-dgx-spark"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-11-10T10:47:34.226Z"
status: "stable"
---

# DeepSeek-V4.1-Flash-1017 EXL3 2.9 bpw with TensorFold on 2× DGX Spark

DeepSeek-V4.1-Flash-1017 EXL3 2.9 bpw with TensorFold on 2× DGX Spark: 55.4 tok/s according to github.com (dataset as of Nov 3, 2026).

- Creator: [tonyd2wild](https://www.contextstudios.ai/local-ai/creators/tonyd2wild.md)
- Engine: TensorFold (bertholomus deepseek-v41-zig @ 3ff3b2a, recipe kit v0.6.1) + 3 patches, both RoCE rails
- Quantization: EXL3 2.9 bpw, all matrices (LibertAI mul1)
- Model family: DeepSeek-V4.1-Flash-1017
- Hardware: dgx-spark x2
- Context: 1048576

## All numbers

- 55.4 tok/s (Everyday; Everyday, 1 request, prose prompt, with DSpark (per recipe)) — [source](https://github.com/tonyd2wild/DeepSeek-V4.1-Flash-TP2-and-TP4-DGX-Sparks/blob/main/runs/2026-10-18-1017-tensorfold-tp2/results/tp2a/bench-tp2a.md)
- decode_tps: 55.43 (1 request) — [source](https://github.com/tonyd2wild/DeepSeek-V4.1-Flash-TP2-and-TP4-DGX-Sparks/blob/main/runs/2026-10-18-1017-tensorfold-tp2/results/tp2a/bench-tp2a.md)
- decode_tps: 73.08 (1 request) — [source](https://github.com/tonyd2wild/DeepSeek-V4.1-Flash-TP2-and-TP4-DGX-Sparks/blob/main/runs/2026-10-18-1017-tensorfold-tp2/results/tp2a/bench-tp2a.md)
- decode_tps: 105.63 (1 request) — [source](https://github.com/tonyd2wild/DeepSeek-V4.1-Flash-TP2-and-TP4-DGX-Sparks/blob/main/runs/2026-10-18-1017-tensorfold-tp2/results/tp2a/bench-tp2a.md)
- prefill_tps: 2134.7 (1 request) — [source](https://github.com/tonyd2wild/DeepSeek-V4.1-Flash-TP2-and-TP4-DGX-Sparks/blob/main/runs/2026-10-18-1017-tensorfold-tp2/results/tp2a/bench-tp2a.md)
- ttft_ms: 243 (1 request) — [source](https://github.com/tonyd2wild/DeepSeek-V4.1-Flash-TP2-and-TP4-DGX-Sparks/blob/main/runs/2026-10-18-1017-tensorfold-tp2/results/tp2a/bench-tp2a.md)

## Weights

- [LibertAIDAI/DeepSeek-V4.1-Flash-1017-EXL3-2.9bpw](https://huggingface.co/LibertAIDAI/DeepSeek-V4.1-Flash-1017-EXL3-2.9bpw) (main, mit)
- [deepseek-ai/DeepSeek-V4.1-Flash-1017](https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017) (base, mit)

[https://github.com/tonyd2wild/DeepSeek-V4.1-Flash-TP2-and-TP4-DGX-Sparks](https://github.com/tonyd2wild/DeepSeek-V4.1-Flash-TP2-and-TP4-DGX-Sparks)

## Related

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