FR
Réserver un appel

Local AI · Recipe · 2× DGX Spark

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).

by tonyd2wild

55.4tok/sEveryday

1 request, prose prompt, with DSpark (per recipe)

Source: github.com
Intelligence (original model) · Artificial Analysisno independent value

≤ 3 bit: quantization may cost quality

Instructions in the README Repo

Engine

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
Context
1,048,576
Parameters
~763B MoE / 16B aktiv
Creator
tonyd2wild
GitHub stars
154
Repo updated
Oct 26, 2026

Measurements

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

Decode · 1 request

  • Everyday (decode)55.4 tok/sProse, C1 per-stream, Prompt-Set v1, T=0, thinking off, 4 Streams / KV-Pool 1.048.576, Lauf tp2a Source 
  • Mixed (decode)73.1 tok/sC1 aggregate über 8 Kategorien (Counting ausgenommen), Prompt-Set v1, T=0; per-stream Mittel 84.16 Source 
  • Peak (decode)106 tok/sKategorie coding, C1 per-stream, tp2a Source 

Prefill by context

  • 93.3352,135 tok/sCold, unique prefix, TTFT 43.723 s Source 

Time to first token

Shorter is better.

  • Prompt not stated243 msMittel über 8 Kategorien, C1, kurze Prompts (0.243 s) Source 

What you need

Hardware
2 × NVIDIA DGX Spark (GB10)
Engine
TensorFold (bertholomus deepseek-v41-zig @ 3ff3b2a, recipe kit v0.6.1) + 3 patches, both RoCE rails
Context
1,048,576 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.
  • Custom kernel required
  • vision
  • tool-calling

Sources

Related recipes

4× DGX Spark

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

by bertholomus

70.9tok/sEveryday

1 request, prose prompt (greedy, thinking off), with DSpark (per recipe) Source 

Intelligenceno independent value
  • ≤ 3 bit: quantization may cost quality
  • Custom kernel required

EXL3 4.0 bpw (4,02 bpw, ~275 GB; eigener Quant)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 graphsWeights Repo Updated Oct 24, 2026

Details
4× DGX Spark

DeepSeek-V4.1-Flash-1017 FP8/MXFP4 with TensorFold on 4× DGX Spark (switchless ring)

by MiaAI-Lab

65.8tok/sEveryday

1 request, prose prompt (T = 0.7, thinking on), with DSpark (per recipe) Source 

Intelligenceno independent value
  • Custom kernel required

FP8 / MXFP4 (official checkpoint as published, no re-quantization)TensorFold native (Zig 0.17.0), BertholomusAI dsv41 family (bertholomus/TensorFold deepseek-v41-zig-tp4 @5940208, kit 6033ea4) + recipe zig/patches, TP4 over a switchless ConnectX-7 ring (./start-switchless.sh), DSpark drafts, CUDA graphsWeights Repo Updated Nov 2, 2026

Details
2× DGX Spark

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

by MiaAI-Lab

63.9tok/sEveryday

1 request, prose prompt (temperature 0.7, thinking on), with DSpark (per recipe) Source 

Intelligenceno independent value
  • ≤ 3 bit: quantization may cost quality
  • Custom kernel required

EXL3 EAQ v1 2.9 bpw (Mia-AiLab; vision tower and DSpark draft blocks included)TensorFold native (Zig 0.17.0), BertholomusAI dsv41 family (bertholomus/TensorFold deepseek-v41-zig @fbbc971) + recipe patches, TP=2 over ConnectX-7 (RoCE), DSpark draftsWeights Repo Updated Nov 2, 2026

Details
2× DGX Spark

DeepSeek-V4.1-Flash-1017 EXL3 2.5 bpw with TensorFold on 2× DGX Spark

by bertholomus

60.5tok/sEveryday

1 request, prose prompt (greedy, thinking off), with DSpark (per recipe) Source 

Intelligenceno independent value
  • ≤ 3 bit: quantization may cost quality
  • Custom kernel required

EXL3 2.5 bpw routed experts (2,52 bpw über die quantisierten Gewichte, ~185 GB; Attention/Shared Experts 4 bpw, DSpark-Drafter 4/6 bpw, Vision-Tower 16 bit)TensorFold native (Zig, TensorFold 1.0.12), BertholomusAI dsv41 family (bertholomus/TensorFold deepseek-v41-zig-tp2, recipe v0.7.3, served engine 6579b756dcd7) + kernel kit v0.7.0, TP=2 über RoCE, DSpark draftsWeights Repo Updated Oct 24, 2026

Details
2× DGX Spark

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

by bertholomus

59.2tok/sEveryday

1 request, prose prompt (temperature 0, thinking off, single run), with DSpark (per recipe) Source 

Intelligenceno independent value
  • ≤ 3 bit: quantization may cost quality
  • Custom kernel required

EXL3 2.9 bpw (LibertAI, Revision afc7aa0a)TensorFold (Elevatormusic/TensorFold @07aa02585f64: TensorFold 0.6.6 line + BertholomusAI DeepSeek-V4.1 family), Launcher Elevatormusic/DeepSeek-V4.1-Flash-1017-EXL3-TensorFold-2x-DGX-Spark, TP=2 über ConnectX-7, DSpark (MTP_DRAFTS=5), MEM_FLOOR_GIB=0Weights Repo Updated Oct 19, 2026

Details

← 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
Cookies

Avec votre consentement, nous utilisons Google Analytics (Google, États-Unis) et notre propre mesure d’audience pour comprendre l’utilisation de notre site. Les stockages strictement nécessaires, comme votre choix de cookies, se font sans consentement. Vous pouvez modifier votre choix à tout moment via « Paramètres des cookies » en pied de page. Politique de confidentialité · Politique relative aux cookies