DE

DeepSeek V3.1 Terminus Bf16

DeepSeekGGUF by createthisUpdated 2025-09-23
Download on Hugging Face
Parameters671B
Context160K
Layers61
Architecturedeepseek2
Smallest quant404.5 GB
Quick answer

DeepSeek V3.1 Terminus Bf16 needs about 406.1 GB of memory at Q4_K_M (a 404.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 404.5 GB (Q4_K_M) to 1342.3 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

DeepSeek V3.1 Terminus Bf16 is a 671B-parameter DeepSeek model in GGUF format, quantized by createthis. Its trained context length is 160K tokens. The repository has 2 quant files, from 404.5 GB (Q4_K_M) to 1342.3 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M404.5 GB (9 parts) 406.1 GB
Too big Get file →
BF161342.3 GB (30 parts) 1343.9 GB
Too big Get file →

What GPU do you need for DeepSeek V3.1 Terminus 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 V3.1 Terminus Bf16 quant should you choose?

Q4_K_M is the usual starting point for DeepSeek V3.1 Terminus Bf16: it balances file size and quality well. Here it is a 404.5 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedeepseek2
Parameters671B (approximate, mixture of experts)
Layers61
Trained context163,840 tokens
KV cache (fp16)130 KB per token

Source

Quantized bycreatethis
FamilyDeepSeek
Licensemit
Downloads (HF)9
Last updated2025-09-23

Frequently asked questions about DeepSeek V3.1 Terminus Bf16

How much VRAM does DeepSeek V3.1 Terminus Bf16 need?

About 406.1 GB at Q4_K_M with an 8K context window. That is the 404.5 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 V3.1 Terminus Bf16 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 406.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of DeepSeek V3.1 Terminus Bf16 GGUF?

It depends on the quant: Q4_K_M is 404.5 GB, BF16 is 1342.3 GB.

What context length does DeepSeek V3.1 Terminus 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 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download DeepSeek V3.1 Terminus Bf16 GGUF?

The files are on Hugging Face in the createthis/DeepSeek-V3.1-Terminus-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 V3.1 Terminus 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.

Similar models

Browse all →

More from createthis

All by createthis →

More DeepSeek models

All DeepSeek →

Other large models

All large models →