Model Detail
DeepSeek-R1
—DeepSeek-R1 is a code generation model with 342.3B 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-R1 reports a Chatbot Arena ELO of 1,422 across 18,451 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-R1 is priced at $1.35/M input tokens and $5.4/M output tokens. Operationally the model offers a 64K-token context window, which matters when sizing it for prompt-heavy or latency-sensitive workloads. Pricing in this range is the working middle of the API market — neither the cheapest nor the most expensive option per token, so cost-fit is usually a function of how much output you generate.
DeepSeek-R1 ships with 342.3B parameters. The published knowledge cutoff is 2024-07-31, so newer events will not be reflected in zero-shot answers without retrieval. Total weight footprint is approximately 684.5 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-R1 have moved +4.2% over the trailing thirty days. 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-R1 is best fit for code completion, repository-scale Q&A, and pair-programming integrations. It is a less obvious choice for one-shot generation of security-critical code without review. 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.
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-
Open-R1: a fully open reproduction of DeepSeek-R1
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
