FR
Réserver un appel

Local AI · Recipe · 1× DGX Spark

DeepSeek-V4.1-Flash Q2_K with llama.cpp on 1× DGX Spark

by vcruz305

2.8tok/sPeak

1 request, best value reported by source, context 2k

Source: github.com
Intelligence (original model) · Artificial Analysis40with thinkingno thinking 25

≤ 3 bit: quantization may cost quality

Instructions in the README Repo

Engine

Engine
llama.cpp Branch runtime/deepseek41
Quantization
GGUF Q2_K (246 GiB)
Model family
DeepSeek-V4.1-Flash
Context
2,048
Creator
vcruz305
GitHub stars
6
Repo updated
Sep 11, 2026

Measurements

Every sourced value of this recipe, each with its condition and source. Bars relative to the largest value in the group.

No sourced measurements for this recipe.

What you need

Hardware
1 × NVIDIA DGX Spark (GB10)
Engine
llama.cpp Branch runtime/deepseek41
Context
2,048 tokens

Notes

What matters before you rebuild it.

  • ≤ 3 bit: quantization may cost qualityAt 3 bit and below the model may answer noticeably worse than the original. The intelligence number refers to the original.
  • Experimental
  • Smoke test only

Sources

Related recipes

← Back to overview

Local AI in your company?

In a workshop we work out which models and which hardware fit your tasks, and build the first agent on your infrastructure.

See the AI workshopBack to overview