DeepSeek-V4-Flash-0731-exl3-hybrid-2.72bpw

anoane/DeepSeek-V4-Flash-0731-exl3-hybrid-2.72bpw

Text Generation52.2B parametersexllamav3License: mit
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
308
Total downloads
308
Gained 7D
Gained 30D
Likes
2
Rank · tracked models
#30,478
this week
Parameters
52.2B
Last source update
Aug 24, 2026

Downloads over time

Rolling recent-window downloads as reported

Likes over time

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-08-24. Charts appear as daily observations accumulate.

Overview

DeepSeek-V4-Flash-0731-exl3-hybrid-2.72bpw is a text generation model published by anoane. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it 3h ago.

Published
Aug 22, 2026
Last updated
Aug 24, 2026
Library
exllamav3
License
mit
Task
Text Generation
Parameters
52,218,679,998
Spaces
Derivative models
Velocity 7D/day
exllamav3safetensorsdeepseek_v4exl3quantizedmixture-of-expertsmoetext-generationconversationalbase_model:deepseek-ai/DeepSeek-V4-Flash-0731base_model:quantized:deepseek-ai/DeepSeek-V4-Flash-0731license:mit

Publisher

anoaneView publisher statistics →

Derived from deepseek-ai/DeepSeek-V4-Flash-0731 (reported by the source; parent not yet tracked).

Similar models

Models similar to DeepSeek-V4-Flash-0731-exl3-hybrid-2.72bpw
ModelDL 30D
Jamba-v0.1ai21labs12.2K
AI21-Jamba-Mini-1.5ai21labs9,062
AI21-Jamba2-Miniai21labs1,219
AI21-Jamba-Mini-1.6ai21labs37
Llama-3_1-Nemotron-51B-Instructnvidia611
Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODERDavidAU127