DE

DeepSeek R1 BF16

DeepSeekGGUF by unslothUpdated 2025-05-30
Download on Hugging Face
Parameters670B
Context160K
Layers61
Architecturedeepseek2
Smallest quant140.2 GB
Quick answer

DeepSeek R1 BF16 needs about 445.9 GB of memory at Q4_K_M (a 404.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 13 quants, from 140.2 GB (IQ1_S) to 1342.3 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 163.7 GB.

DeepSeek R1 BF16 – 670B parameters, 163,840 token context, MIT licensed

DeepSeek R1 BF16 is a 670 billion‑parameter model trained with large‑scale reinforcement learning. It supports coding and reasoning tasks and offers a 163,840‑token context window. The model is available in GGUF format and is MIT licensed.

Good at

  • Coding tasks
  • Complex reasoning
  • Long context handling

Limits

  • Requires large VRAM for full precision
  • No vision support
  • MIT license limits commercial use without attribution

Best for

  • Developers building reasoning‑heavy applications
  • Researchers testing RL‑trained models
  • Educators needing long‑context code examples

Who it’s for. Engineers and researchers who need a high‑capacity reasoning model and have sufficient GPU memory. The model is suitable for those who can run it locally and are comfortable with GGUF and llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S140.2 GB (3 parts) 181.7 GB
Too big Get file →
IQ1_M168.9 GB (4 parts) 210.4 GB
Too big Get file →
IQ2_XXS196.2 GB (4 parts) 237.6 GB
Too big Get file →
Q2_K_XS221.3 GB (5 parts) 262.7 GB
Too big Get file →
Q2_K_XL226.6 GB (5 parts) 268.0 GB
Too big Get file →
Q2_K244.0 GB (5 parts) 285.5 GB
Too big Get file →
Q2_K_L244.2 GB (5 parts) 285.7 GB
Too big Get file →
Q3_K_M319.2 GB (7 parts) 360.6 GB
Too big Get file →
Q4_K_M404.4 GB (9 parts) 445.9 GB
Too big Get file →
Q5_K_M475.4 GB (10 parts) 516.8 GB
Too big Get file →
Q6_K550.8 GB (12 parts) 592.2 GB
Too big Get file →
Q8_0713.3 GB (15 parts) 754.7 GB
Too big Get file →
BF161342.3 GB (30 parts) 1383.7 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (≈445 GB memory at 8k context). For 12 GB VRAM, Q3_K_M (≈360 GB). For 24 GB VRAM, Q2_K (≈286 GB). The BF16 file is 1.34 TB and requires ~1.38 TB VRAM at 8k context, so it is only practical on very large GPU setups.

What GPU do you need for DeepSeek R1 BF16?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which DeepSeek R1 BF16 quant should you choose?

Q4_K_M is the usual starting point for DeepSeek R1 BF16: it balances file size and quality well. Here it is a 404.4 GB file.

The Q8_0 file is 713.3 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ1_S at 140.2 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedeepseek2
Parameters670B (approximate, mixture of experts)
Layers61
Trained context163,840 tokens
KV cache (fp16)4880 KB per token

Source

Quantized byunsloth
FamilyDeepSeek
Licensemit
Downloads (HF)31,540
Last updated2025-05-30

Frequently asked questions about DeepSeek R1 BF16

How much VRAM does DeepSeek R1 BF16 need?

About 445.9 GB at Q4_K_M with an 8K context window. That is the 404.4 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run DeepSeek R1 BF16 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 181.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of DeepSeek R1 BF16 GGUF?

It depends on the quant: IQ1_S is 140.2 GB, IQ1_M is 168.9 GB, IQ2_XXS is 196.2 GB, Q2_K_XS is 221.3 GB, Q2_K_XL is 226.6 GB, Q2_K is 244.0 GB and 7 more.

What context length does DeepSeek R1 BF16 support?

The GGUF header lists a trained context length of 163,840 tokens (160K). The KV cache grows with the context you use: about 40.9 GB at 8K and 163.7 GB at 32K.

Where can I download DeepSeek R1 BF16 GGUF?

The files are on Hugging Face in the unsloth/DeepSeek-R1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does DeepSeek R1 BF16 use?

Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run DeepSeek R1 BF16 on 8 GB VRAM?

No. The smallest quant requires 445 GB VRAM at 8k context, far above 8 GB.

Does the model support image input?

No, DeepSeek R1 BF16 does not have vision capabilities.

What license applies to this model?

The model is MIT licensed, allowing free use with attribution.

Other GGUFs of DeepSeek-R1

Similar models

Browse all →

More from unsloth

All by unsloth →

More DeepSeek models

All DeepSeek →

Other large models

All large models →