DeepSeek-V4-Flash-MTP-DSpark-MLX

inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX

Text Generation20.9B parametersmlx
Tracked by OpenModelStats since September 8, 2026View on Hugging Face ↗
Downloads 30D
239
Total downloads
2,570
Gained 7D
+58(increase)
2.4%(up) vs baseline
Gained 30D
—
Likes
1
+0 in 7D
Rank · tracked models
#48,537
859(down 859 places)this week
Parameters
20.9B
Last source update
Aug 5, 2026
Momentum
34.7
  • DeepSeek-V4-Flash-MTP-DSpark-MLX gained 58 downloads during the last seven tracked days.
  • It moved from #14444 to #14822 among tracked Text Generation models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

DeepSeek-V4-Flash-MTP-DSpark-MLX is a text generation model published by inferencerlabs. OpenModelStats has tracked the model since Sep 8, 2026, most recently observing it Oct 7, 2026.

Published
Aug 2, 2026
Last updated
Aug 5, 2026
Library
mlx
License
—
Task
Text Generation
Parameters
20,904,912,743
Spaces
0
Derivative models
—
Velocity 7D/day
8
mlxsafetensorsdeepseek_v4_dsparktext-generationenbase_model:deepseek-ai/DeepSeek-V4-Flash-0731base_model:quantized:deepseek-ai/DeepSeek-V4-Flash-07318-bitregion:us

Model family

Based on base-model relationships reported by the source's metadata.

Similar models

Models similar to DeepSeek-V4-Flash-MTP-DSpark-MLX
ModelDL 30D
gpt-oss-20b-MXFP4-Q8mlx-community241.3K
gpt-oss-20b-OptiQ-4bitmlx-community4,832
gpt-oss-20b-MLX-8bitlmstudio-community3,870
gpt-oss-20b-MXFP4-Q4mlx-community2,649
OpenAI-gpt-oss-20B-INSTRUCT-Heretic-Uncensored-MXFP4-q8-hi-mlxnightmedia1,960
gpt-oss-20b-TurboQuant-MLX-4bitmajentik422
inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX — Downloads, Growth & Stats | OpenModelStats