Model · DeepSeek-R1 · January 2025 Live · Hugging Face

DeepSeek-R1 671B

A 671 billion-parameterHow many numbers the model learned during training — the usual rough measure of its size. mixture-of-expertsA model split into parts where only a few run for each word, so it answers faster than its size suggests. model using ~37 billion parameters per token from DeepSeek. Open reasoning model plus distilled dense models.

Size: 671B37B active
Memory to run: ~169 GB estimatesmallest, 8K ctx
Context: 160Ktokens
License: PermissiveMIT License
Updated: 18 Sept 2026

Compare

Where it runs

Best-fitting version on each reference system, at an 8K contextHow much text the model can consider at once, counted in tokens — roughly ¾ of a word each..

Your hardware →

Runs well 0

None of the reference systems.

Slowly (CPU or offload) 1

A100 80GB server~21 tok/s estimate

Too large 18

Measured throughput

No performance measurements recorded yet.

Versions & downloads

Each version is a separate set of weights. Expand one for its downloads: quantizationStoring each of the model’s numbers with fewer bits, so the file is smaller and needs less memory. trades a little quality for a much smaller file, and the memory column adds the working memoryExtra space the model needs while it answers. It grows with the length of the conversation, on top of the file itself. a conversation needs on top.

DeepSeek-R1Trained to think step by step before answering; slower, stronger on hard problems. · DeepSeek · 3 downloadsPermissive

Good for: ChatReasoningCodingLong context
Publisher: DeepSeek
License: MIT License · commercial use allowed
Released: 20 Jan 2025
huggingface: deepseek-ai/DeepSeek-R1

Contributions are not open yet, so there is nothing here from members.

Quantization	Format	Bits	Download	Memory @ 8K	Publisher
Download FP8fp8	safetensors	8.1	633 GiB	~659.1 GiB estimate	DeepSeekdeepseek-ai/DeepSeek-R1
Download Q3_K_Mk quant	gguf	3.91	305 GiB	~318.7 GiB estimate	Unsloth AIunsloth/DeepSeek-R1-GGUF
Download IQ2_XXSi quant	gguf	2.06	161 GiB	~168.4 GiB estimate	Unsloth AIunsloth/DeepSeek-R1-GGUF

Benchmarks

Each benchmarkA fixed set of questions every model is given, so their scores can be compared on the same task. score is labelled with who produced it. Developer-reported scores use each lab’s own prompts and settings; a benchmark that runs every model itself uses one setup for all. Bars are relative to the best open result.

Benchmark	DeepSeek-R1
Benchmark GPQA DiamondAccuracy	71.5src
Benchmark LiveCodeBenchpass@1	65.9src
Benchmark MATH-500Accuracy	97.3src
Benchmark MMLU-ProAccuracy	84.0src

developer-reported

Community

Benchmark runs and reviews from people running it on their own hardware.

Benchmark runs

Contributions are not open yet, so there is nothing here from members.

Reviews

Contributions are not open yet, so there is nothing here from members.

Details & sources

Architecture

Parameters: 671B
Active / token: 37B
Architecture: Mixture of experts
Layers: 61
Attention heads: 128
KV heads: 128
Head dim: 128
KV cache @ 8K (fp16): 0.54 GiB
Max context: 163,840 tokens

Lineage

How this model’s versions relate to each other and to other models.

DeepSeek-R1 reasoning

DeepSeek-R1-Distill-Qwen-7B distilled from DeepSeek-R1

DeepSeek-R1-Distill-Qwen-32B distilled from DeepSeek-R1

Sources

Hugging Face Hub (live source, 1 record, 18 Sept 2026)
Mutinai illustrative fixtures (illustrative fixture, 1 record, 13 Sept 2026)

External identifiers

huggingface deepseek-ai/DeepSeek-R1

Field history

license = "mit" — Hugging Face Hub (current)

Timeline

20 Jan 2025
DeepSeek-R1 and distilled models released under MIT