---
type: "Article"
title: "DeepSeek-V4.1-Flash-1017 EXL3 4.0 bpw with TensorFold on 4× DGX Spark"
description: "DeepSeek-V4.1-Flash-1017 EXL3 4.0 bpw with TensorFold on 4× DGX Spark: recipe by bertholomus with speed, condition and source for every number, weights and license."
resource: "https://www.contextstudios.ai/local-ai/bertholomus--deepseek-v4.1-flash-1017-tensorfold-exl3-4.0bpw-4x-dgx-spark"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-11-11T03:30:11.656Z"
status: "stable"
---

# DeepSeek-V4.1-Flash-1017 EXL3 4.0 bpw with TensorFold on 4× DGX Spark

DeepSeek-V4.1-Flash-1017 EXL3 4.0 bpw with TensorFold on 4× DGX Spark: 70.9 tok/s according to github.com (dataset as of Nov 3, 2026).

- Creator: [bertholomus](https://www.contextstudios.ai/local-ai/creators/bertholomus.md)
- Engine: TensorFold native (Zig, TensorFold 1.0.12), BertholomusAI dsv41 family (bertholomus/TensorFold deepseek-v41-zig-tp4 @0a0b69a, recipe v0.3.5) + kernel kit (362 files), TP4 über RoCE, DSpark drafts, CUDA graphs
- Quantization: EXL3 4.0 bpw (4,02 bpw, ~275 GB; eigener Quant)
- Model family: DeepSeek-V4.1-Flash-1017
- Hardware: dgx-spark x4
- Context: 1048576

## All numbers

- 70.9 tok/s (Everyday; Everyday, 1 request, prose prompt (greedy, thinking off), with DSpark (per recipe)) — [source](https://github.com/bertholomus/deepseek-v4.1-tensorfold-tp4-4xgb10#speed)
- decode_tps: 70.9 (1 request) — [source](https://github.com/bertholomus/deepseek-v4.1-tensorfold-tp4-4xgb10#speed)
- decode_tps: 183.7 (1 request) — [source](https://github.com/bertholomus/deepseek-v4.1-tensorfold-tp4-4xgb10#speed)
- prefill_tps: 2937.1 (1 request) — [source](https://github.com/bertholomus/deepseek-v4.1-tensorfold-tp4-4xgb10#v035-what-changed)

## Weights

- [bertholomus/DeepSeek-V4.1-Flash-1017-EXL3-4.0bpw](https://huggingface.co/bertholomus/DeepSeek-V4.1-Flash-1017-EXL3-4.0bpw) (main, mit)
- [deepseek-ai/DeepSeek-V4.1-Flash-1017](https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017) (base, mit)

[https://github.com/bertholomus/deepseek-v4.1-tensorfold-tp4-4xgb10](https://github.com/bertholomus/deepseek-v4.1-tensorfold-tp4-4xgb10)

## Related

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