Model Detail
DeepSeek-V4-Flash-Base
▲ 1.2%DeepSeek-V4-Flash-Base is an AI model with 146.0B parameters released by DeepSeek. It has accumulated 9K downloads on Hugging Face since publication.
DeepSeek-V4-Flash-Base ships with 146.0B parameters. Total weight footprint is approximately 292.0 GB, which is the relevant figure when planning local-inference VRAM.
Downloads of DeepSeek-V4-Flash-Base have moved +1.2% over the past 24 hours, +264.5% over the trailing seven days. That puts the model in active uptrend territory; a sustained move of this size usually reflects a recent release, a viral integration, or a benchmark surprise rather than steady-state demand. These numbers are signal, not guarantee — week-over-week download counts on Hugging Face also reflect mirror traffic, CI scrapes, and one-off benchmarking runs.
DeepSeek-V4-Flash-Base is best fit for general-purpose AI workloads. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
Deploying DeepSeek 175B Locally on a Single Consumer-Grade RTX 4060 Laptop with 32GB RAM for 200k-Scale Protein-Ligand Virtual Screening
arXiv:2608.30877v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have demonstrated exceptional performance in protein-ligand interaction prediction, but state-of-the-art pipelines for large-scale virtual screening almost exclusively rely on high-end GPU clusters with h
SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD
arXiv:2607.20145v2 Announce Type: replace Abstract: Full-parameter post-training of trillion-parameter-scale MoE models introduces substantial system-level challenges for large-scale distributed training, including severe memory pressure, non-overlapped communication overhead, and inefficient kernel
FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention
arXiv:2606.09079v3 Announce Type: replace-cross Abstract: Conventional LLMs keep the full KV cache loaded during decoding, causing a severe GPU memory bottleneck for ultra-long context serving. In this report, we propose \textbf{Lookahead Sparse Attention (LSA)}, a novel inference paradigm powered b
DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
arXiv:2606.19348v1 Announce Type: cross Abstract: We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models -- DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSeek-V4-Flash with 284B parameters (13B activated) -- both supporting a
Instruction Finetuning DeepSeek-R1-8B Model Using LoRA and NEFTune
arXiv:2606.10392v1 Announce Type: new Abstract: Financial named-entity recognition (NER) is essential for translating unstructured financial reports and news into structured knowledge graphs. However, general-purpose large language models (LLMs) often misclassify financial entities or ignore domain-
Attribution-Guided and Coverage-Maximized Pruning for Structural MoE Compression
arXiv:2606.18304v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models scale compute efficiently, yet remain expensive to deploy due to their substantial memory footprint and inference overhead. Prior compression methods mainly operate at the expert level, either removing entire experts o
