DE

Deepseek ai.DeepSeek V3.1 Terminus BF16

DeepSeekGGUF by DevQuasarUpdated 2025-09-24
Download on Hugging Face
Parameters671B
Context160K
Layers61
Architecturedeepseek2
Smallest quant1.0 GB
Quick answer

Deepseek ai.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 11 quants, from 1.0 GB to 1342.3 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

DeepSeek V3.1 Terminus BF16 – 671B parameters, 163,840 token context

DeepSeek V3.1 Terminus BF16 is a 671‑billion‑parameter model with a 163,840‑token context window. It supports reasoning and tool usage. The model is released under the MIT license.

Good at

  • Reasoning
  • Tool usage
  • Large context handling

Limits

  • No vision support
  • Requires large VRAM for full precision
  • Limited to 163,840 token context

Best for

  • Complex reasoning tasks
  • Agent‑based workflows
  • Long‑form content generation

Who it’s for. Developers building AI agents that need extensive context and reasoning. Researchers requiring a large‑parameter model with tool integration. Teams needing a permissively licensed model for internal use.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—1.0 GB 2.6 GB
Fits Get file →
IQ1_M149.1 GB (12 parts) 150.6 GB
Too big Get file →
IQ2_XXS174.6 GB (13 parts) 176.2 GB
Too big Get file →
IQ2_XS195.2 GB (15 parts) 196.8 GB
Too big Get file →
Q2_K244.1 GB (20 parts) 245.7 GB
Too big Get file →
Q3_K_M319.3 GB (25 parts) 320.9 GB
Too big Get file →
Q4_K_M404.5 GB (31 parts) 406.1 GB
Too big Get file →
Q5_K_M475.4 GB (36 parts) 477.0 GB
Too big Get file →
Q6_K550.9 GB (44 parts) 552.5 GB
Too big Get file →
Q8_0713.3 GB (59 parts) 714.9 GB
Too big Get file →
F161342.3 GB (88 parts) 1343.9 GB
Too big Get file →

For 8 GB VRAM, use IQ1_M (149.06 GB file, 150.6 GB memory at 8 k context). For 16 GB VRAM, use Q4_K_M (404.49 GB file, 406.1 GB memory). For 32 GB VRAM, use Q6_K (550.92 GB file, 552.5 GB memory). Estimates are approximate.

What GPU do you need for Deepseek ai.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: the best quant that fits is the main file (1.0 GB file, about 2.6 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (1.0 GB file, about 2.6 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (1.0 GB file, about 2.6 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (1.0 GB file, about 2.6 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (1.0 GB file, about 2.6 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (1.0 GB file, about 2.6 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (1.0 GB file, about 2.6 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (1.0 GB file, about 2.6 GB in use).

Which Deepseek ai.DeepSeek V3.1 Terminus BF16 quant should you choose?

Q4_K_M is the usual starting point for Deepseek ai.DeepSeek V3.1 Terminus BF16: it balances file size and quality well. Here it is a 404.5 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 the first one in the table at 1.0 GB, with the quality trade-offs that come with fewer bits.

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 byDevQuasar
FamilyDeepSeek
Licensemit
Downloads (HF)1,375
Last updated2025-09-24

Frequently asked questions about Deepseek ai.DeepSeek V3.1 Terminus BF16

How much VRAM does Deepseek ai.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 ai.DeepSeek V3.1 Terminus BF16 on an 8 GB GPU?

Yes, with the smaller files: the 1.0 GB file needs about 2.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Deepseek ai.DeepSeek V3.1 Terminus BF16 GGUF?

It depends on the quant: file is 1.0 GB, IQ1_M is 149.1 GB, IQ2_XXS is 174.6 GB, IQ2_XS is 195.2 GB, Q2_K is 244.1 GB, Q3_K_M is 319.3 GB and 5 more.

What context length does Deepseek ai.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 ai.DeepSeek V3.1 Terminus BF16 GGUF?

The files are on Hugging Face in the DevQuasar/deepseek-ai.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 ai.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.

Can I run this model on 8 GB VRAM?

Use the IQ1_M quantized file; it requires about 150.6 GB memory at 8 k context, which is not feasible on 8 GB VRAM. Smaller quants are not available.

Does the model support vision?

No, the model does not have vision capabilities.

What license does the model use?

The model is licensed under the MIT License.

Other GGUFs of DeepSeek-V3.1-Terminus

Similar models

Browse all →

More from DevQuasar

All by DevQuasar →

More DeepSeek models

All DeepSeek →

Other large models

All large models →