DE

DeepSeek V3.2 Speciale Bf16 Safetensors

DeepSeekGGUF by ubergarmUpdated 2026-01-09
Download on Hugging Face
Parameters671B
Context160K
Layers61
Architecturedeepseek2
Smallest quant156.9 GB
Quick answer

DeepSeek V3.2 Speciale Bf16 Safetensors needs about 194.3 GB of memory at its main file (a 192.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 4 quants, from 156.9 GB to 498.7 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

DeepSeek V3.2 Speciale Bf16 Safetensors is a 671B-parameter DeepSeek model in GGUF format, quantized by ubergarm. Its trained context length is 160K tokens. The repository has 4 quant files, from 156.9 GB to 498.7 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—156.9 GB (5 parts) 158.5 GB
Too big Get file →
—192.7 GB (5 parts) 194.3 GB
Too big Get file →
—312.4 GB (8 parts) 313.9 GB
Too big Get file →
—498.7 GB (12 parts) 500.3 GB
Too big Get file →

What GPU do you need for DeepSeek V3.2 Speciale Bf16 Safetensors?

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 V3.2 Speciale Bf16 Safetensors quant should you choose?

If memory is tight, the smallest file is the first one in the table at 156.9 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 byubergarm
FamilyDeepSeek
Licensemit
Downloads (HF)134
Last updated2026-01-09

Frequently asked questions about DeepSeek V3.2 Speciale Bf16 Safetensors

How much VRAM does DeepSeek V3.2 Speciale Bf16 Safetensors need?

About 194.3 GB at its main file with an 8K context window. That is the 192.7 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 V3.2 Speciale Bf16 Safetensors on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 158.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of DeepSeek V3.2 Speciale Bf16 Safetensors GGUF?

It depends on the quant: file is 156.9 GB, file is 192.7 GB, file is 312.4 GB, file is 498.7 GB.

What context length does DeepSeek V3.2 Speciale Bf16 Safetensors 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 V3.2 Speciale Bf16 Safetensors GGUF?

The files are on Hugging Face in the ubergarm/DeepSeek-V3.2-Speciale-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 V3.2 Speciale Bf16 Safetensors 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 ubergarm

All by ubergarm →

More DeepSeek models

All DeepSeek →

Other large models

All large models →