DE

DeepSeek V3.1 Base

DeepSeekGGUF by bartowskiUpdated 2025-08-21
Download on Hugging Face
Parameters671B
Context160K
Layers61
Architecturedeepseek2
Smallest quant1.0 GB
Quick answer

DeepSeek V3.1 Base needs about 410.8 GB of memory at Q4_K_M (a 409.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 19 quants, from 1.0 GB to 713.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

DeepSeek V3.1 Base – a 671B parameter hybrid reasoning model

DeepSeek V3.1 Base is a 671B parameter model built on the deepseek2 architecture. It supports reasoning and tool calling and is trained with a 163840 token context window. The model is available in multiple GGUF quantizations.

Good at

  • Reasoning tasks
  • Tool calling
  • Long context processing

Limits

  • No vision support
  • License not specified
  • Large memory requirement

Best for

  • Chatbot agents
  • Tool‑enabled workflows
  • Long‑document summarization

Who it’s for. Developers building AI assistants that need reasoning and tool usage. The model is suitable for applications that can handle large memory footprints and long context windows.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—1.0 GB 2.6 GB
Fits Get file →
IQ1_S141.3 GB (4 parts) 142.8 GB
Too big Get file →
IQ1_M147.4 GB (4 parts) 149.0 GB
Too big Get file →
IQ2_XXS164.1 GB (5 parts) 165.6 GB
Too big Get file →
IQ2_XS188.4 GB (5 parts) 190.0 GB
Too big Get file →
IQ2_S189.6 GB (5 parts) 191.2 GB
Too big Get file →
IQ2_M215.0 GB (6 parts) 216.6 GB
Too big Get file →
Q2_K237.8 GB (7 parts) 239.4 GB
Too big Get file →
Q2_K_L238.7 GB (7 parts) 240.3 GB
Too big Get file →
IQ3_XXS267.6 GB (7 parts) 269.2 GB
Too big Get file →
IQ3_XS277.1 GB (8 parts) 278.7 GB
Too big Get file →
IQ3_M307.9 GB (8 parts) 309.5 GB
Too big Get file →
Q3_K_M307.9 GB (8 parts) 309.5 GB
Too big Get file →
Q3_K_XL320.5 GB (9 parts) 322.1 GB
Too big Get file →
IQ4_XS360.0 GB (10 parts) 361.6 GB
Too big Get file →
Q4_0386.4 GB (10 parts) 388.0 GB
Too big Get file →
Q4_K_M409.2 GB (11 parts) 410.8 GB
Too big Get file →
Q6_K552.4 GB (15 parts) 554.0 GB
Too big Get file →
Q8_0713.3 GB (20 parts) 714.9 GB
Too big Get file →

For a 16 GB VRAM setup, Q4_K_M (409.23 GB file, 410.8 GB memory at 8 k context) is the smallest viable quant. For 32 GB VRAM, Q6_K (552.45 GB file, 554 GB memory) offers higher quality. No quant fits an 8 GB VRAM budget.

What GPU do you need for DeepSeek V3.1 Base?

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 V3.1 Base quant should you choose?

Q4_K_M is the usual starting point for DeepSeek V3.1 Base: it balances file size and quality well. Here it is a 409.2 GB file.

The Q8_0 file is 713.3 GB, about 1.7 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 bybartowski
FamilyDeepSeek
Downloads (HF)716
Last updated2025-08-21

Frequently asked questions about DeepSeek V3.1 Base

How much VRAM does DeepSeek V3.1 Base need?

About 410.8 GB at Q4_K_M with an 8K context window. That is the 409.2 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 Base 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 V3.1 Base GGUF?

It depends on the quant: file is 1.0 GB, IQ1_S is 141.3 GB, IQ1_M is 147.4 GB, IQ2_XXS is 164.1 GB, IQ2_XS is 188.4 GB, IQ2_S is 189.6 GB and 13 more.

What context length does DeepSeek V3.1 Base 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 Base GGUF?

The files are on Hugging Face in the bartowski/deepseek-ai_DeepSeek-V3.1-Base-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run DeepSeek V3.1 Base on 8 GB VRAM?

No quant of this model fits an 8 GB VRAM budget; the smallest quant requires over 400 GB of memory at 8 k context.

Which quant is best for 16 GB VRAM?

Use Q4_K_M; it is the smallest quant that can be loaded on 16 GB VRAM, with an estimated 410.8 GB memory at 8 k context.

What is the context length of this model?

The model was trained with a 163840 token context window.

Other GGUFs of DeepSeek-V3.1-Base

Similar models

Browse all →

More from bartowski

All by bartowski →

More DeepSeek models

All DeepSeek →

Other large models

All large models →