Model Detail
DeepSeek-V4-Flash
—DeepSeek-V4-Flash is a large language model with 145.5B 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 reports a Chatbot Arena ELO of 1,436 across 45,050 votes. Other benchmark slots are still empty in our dataset, so this single figure is best read as a partial picture rather than a full evaluation.
DeepSeek-V4-Flash is priced at $0.19/M input tokens and $0.38/M output tokens. Operationally the model offers a 1049K-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 145.5B parameters. Total weight footprint is approximately 290.9 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.
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 (1049K 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.
US orders federal agencies to remove China’s DeepSeek AI from their systems
The U.S. has ordered federal civilian agencies to remove DeepSeek products and third-party services built using its technology, citing national security concerns.
Adapting Tree-Structured Speculative Decoding to DeepSeek-V4 for Efficient Inference
arXiv:2609.24698v1 Announce Type: cross Abstract: Repeated execution of the target model during autoregressive decoding is a major source of LLM inference latency. Unlike linear speculation, which follows a single candidate chain, tree-structured speculation retains multiple branches from shared pre
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
arXiv:2609.19969v1 Announce Type: new Abstract: The widespread adoption of long-horizon agents has made model workloads increasingly input-heavy. Although prior work has substantially reduced the cost of long-context computation, prefill remains computationally expensive, and large KV caches continu
Anthropic details distillation campaigns from Alibaba, Moonshot AI, and DeepSeek
A new report released Thursday by Anthropic alleges persistent distillation attacks by China-based AI companies, which have escalated in recent months as competition in the space has intensified.
RedKnot-MLA: Multi-Head Offline-Online Reuse for DeepSeek-V4 Long-Context Serving
arXiv:2609.07008v1 Announce Type: new Abstract: Multi-head latent attention (MLA) exposes many logical query heads through one packed latent KV stream. This representation is memory efficient, but it removes the physical per-head cache boundary assumed by conventional head-wise reuse. We present our
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
