Model Detail
DeepSeek-V4-Flash
▲ 1.7%DeepSeek-V4-Flash is a large language model with 79.0B parameters released by DeepSeek. The model is registered under the text-generation pipeline tag on Hugging Face, and supports text->text inputs, distributed under the permissive mit license.
DeepSeek-V4-Flash is priced at $0.19/M input tokens and $0.51/M output tokens. Operationally the model offers a 1000K-token context window, which matters when sizing it for prompt-heavy or latency-sensitive workloads. At this input rate the model sits in the commodity tier and is suitable for high-volume workloads where per-call cost dominates the decision.
DeepSeek-V4-Flash ships with 79.0B parameters. Total weight footprint is approximately 158.1 GB, which is the relevant figure when planning local-inference VRAM. The mit license is permissive, allowing commercial deployment and derivative work without per-seat fees, though attribution requirements still apply.
Downloads of DeepSeek-V4-Flash have moved +1.7% over the past 24 hours. That is a slight downtrend, consistent with normal cooling as newer models compete for the same workloads. 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 is best fit for general-purpose chat and instruction-following workloads, high-volume batch jobs where per-call cost dominates the budget, and long-context tasks such as full-codebase analysis or book-length summarization (1000K tokens). 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.
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-
DeepSeekMath Meets Order Book: Group-Aware Policy Optimization for High-Frequency Directional Trading
arXiv:2605.25527v1 Announce Type: new Abstract: This paper studies reinforcement learning for high-frequency trading on limit order books by pairing an Order-Flow-based state model with policy-gradient methods. Instead of value-based RL techniques like tabular Q-learning, our approach deploys policy
SoK: A Comprehensive Security Analysis of Jailbreak Resilience in GPT and DeepSeek Models
arXiv:2506.18543v2 Announce Type: replace-cross Abstract: The rapid proliferation of Large Language Models (LLMs) has heightened concerns regarding their exposure to jailbreak attacks, which craft adversarial inputs designed to elicit unsafe content. Although proprietary models such as GPT-4 have be
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
