OpenModelStats

DeepSeek-V4-Flash-W4A16-FP8-MTP

canada-quant/DeepSeek-V4-Flash-W4A16-FP8-MTP

Text Generation50.7B parametersvllmLicense: mit
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
11.7K
Total downloads
34.4K
Gained 7D
—
Gained 30D
—
Likes
20
Rank · tracked models
#7,324
–this week
Parameters
50.7B
Last source update
May 30, 2026
7D30D90D1YAll
Total downloadsGained per dayRolling recent downloads

Downloads over time

Cumulative total downloads observed by OpenModelStats

Not enough tracked history yet for a chart.

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

Likes over time

Not enough tracked history yet for a chart.

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

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-W4A16-FP8-MTP is a text generation model published by canada-quant. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it 3h ago.

Published
May 22, 2026
Last updated
May 30, 2026
Library
vllm
License
mit
Task
Text Generation
Parameters
50,709,699,698
Spaces
—
Derivative models
—
Velocity 7D/day
—
vllmsafetensorsdeepseek_v4deepseekcompressed-tensorsw4a16gptqfp8mtpspeculative-decodingmixture-of-expertsmoe

Publisher

canada-quantView publisher statistics →

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

Similar models

Models similar to DeepSeek-V4-Flash-W4A16-FP8-MTP
ModelDL 30D
JoyAI-LLM-Flash-MXFP8-last-6-BF16zianglih27.5K
DeepSeek-V4-Flash-TQ-Q5.6-MLXlemuralabs1,348
Kimi-K3-mlx-reap160-2bitmlx-community3,163
Llama-3_1-Nemotron-51B-Instructnvidia611
Llama-3_3-Nemotron-Super-49B-v1_5-FP8nvidia239.2K
Llama-3_3-Nemotron-Super-49B-v1nvidia188.7K