DeepSeek-V4.1-Flash-1017-Tandem-VQ2

ewhacc/DeepSeek-V4.1-Flash-1017-Tandem-VQ2

Text Generation127B parametersvllmLicense: mit
Tracked by OpenModelStats since November 9, 2026View on Hugging Face ↗
Downloads 30D
735
Total downloads
735
Gained 7D
—
Gained 30D
—
Likes
2
Rank · tracked models
#47,235
14299(up 14299 places)this week
Parameters
127B
Last source update
Nov 19, 2026
  • It moved from #19003 to #13391 among tracked Text Generation models this week.

Downloads over time

Rolling recent-window downloads as reported

Likes over time

Rank among tracked models

Lower is better

Overview

DeepSeek-V4.1-Flash-1017-Tandem-VQ2 is a text generation model published by ewhacc. OpenModelStats has tracked the model since Nov 9, 2026, most recently observing it 36 min ago.

Published
Nov 5, 2026
Last updated
Nov 19, 2026
Library
vllm
License
mit
Task
Text Generation
Parameters
127,460,775,394
Spaces
—
Derivative models
—
Velocity 7D/day
—
vllmsafetensorsdeepseek_v41moeexpert-offload2-bitvector-quantizationtandemtext-generationbase_model:deepseek-ai/DeepSeek-V4.1-Flash-1017base_model:quantized:deepseek-ai/DeepSeek-V4.1-Flash-1017license:mit

Publisher

ewhaccView publisher statistics →

Derived from deepseek-ai/DeepSeek-V4.1-Flash-1017 (reported by the source; parent not yet tracked).

Similar models

Models similar to DeepSeek-V4.1-Flash-1017-Tandem-VQ2
ModelDL 30D
Ling-3.0-flashinclusionAI8,392
Ling-3.0-flash-SanteinclusionAI2,988
Ling-3.0-flash-FininclusionAI2,749
Ling-3.0-flash-Sante-fp8inclusionAI677
Ling-3.0-flash-int4inclusionAI614
Ling-3.0-flash-fp8inclusionAI508