HF Model & Benchmark Matrix

dflash_qwen3_4b_block7

deepseek-ai/dflash_qwen3_4b_block7

kind

original

quant

bf16 (16-bit)

family

qwen

modality

—

root model

deepseek-ai/dflash_qwen3_4b_block7

provider

deepseek-ai

license

—

language

—

context

—

library

—

vRAM (GB)

—

size on disk

—

downloads

2,212

likes

2

created

—

last modified

2026-06-28T12:30:04+00:00 (2026)

huggingface

https://huggingface.co/deepseek-ai/dflash_qwen3_4b_block7

tags

safetensorsqwen3region:us

Benchmark scores (0)

no scores extracted for this variant.

Discussions (0)

none scraped.