DE

deepseek-ai_deepseek-coder-1.3b-base

DeepSeekGGUF by TheBlokeUpdated 2023-11-05
Download on Hugging Face
Parameters1.35B
Context16K
Layers24
Architecturellama
Smallest quant0.6 GB
Quick answer

deepseek-ai_deepseek-coder-1.3b-base needs about 3.0 GB of memory at Q4_K_M (a 0.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.6 GB (Q2_K) to 1.4 GB (Q8_0).

DeepSeek Coder 1.3B Base – a 1.3B parameter code model in GGUF format

DeepSeek Coder 1.3B Base is a 1.3B parameter model trained on 2 trillion tokens, with a 16K context window. It is optimized for code completion and infilling across multiple programming languages. The model is available in several GGUF quantisations for local inference.

Good at

  • Code completion
  • Project‑level code infilling
  • Multi‑language programming support

Limits

  • Requires 8K context for memory estimates
  • No vision or multimodal support
  • License is MIT with model‑specific terms

Best for

  • Small‑to‑medium code projects
  • Rapid prototyping of code snippets
  • Educational coding tools

Who it’s for. Developers and researchers who need a lightweight, open‑source code model for local inference. The model supports commercial use under its MIT license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.6 GB 2.7 GB
Fits Get file →
Q3_K_S0.7 GB 2.8 GB
Fits Get file →
Q3_K_M0.7 GB 2.8 GB
Fits Get file →
Q3_K_L0.7 GB 2.9 GB
Fits Get file →
Q4_00.8 GB 2.9 GB
Fits Get file →
Q4_K_S0.8 GB 2.9 GB
Fits Get file →
Q4_K_M0.9 GB 3.0 GB
Fits Get file →
Q5_00.9 GB 3.0 GB
Fits Get file →
Q5_K_S1.0 GB 3.1 GB
Fits Get file →
Q5_K_M1.0 GB 3.1 GB
Fits Get file →
Q6_K1.2 GB 3.3 GB
Fits Get file →
Q8_01.4 GB 3.5 GB
Fits Get file →

For 8 GB VRAM, Q4_K_M (0.87 GB) or Q5_K_M (1 GB) are suitable, offering a balance of size and performance. If memory is tighter, Q3_K_M (0.70 GB) or Q4_0 (0.78 GB) can be used. Larger VRAM allows Q5_0 (0.94 GB) or Q6_K (1.17 GB).

What GPU do you need for deepseek-ai_deepseek-coder-1.3b-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 Q8_0 (1.4 GB file, about 3.5 GB in use).

Which deepseek-ai_deepseek-coder-1.3b-base quant should you choose?

Q4_K_M is the usual starting point for deepseek-ai_deepseek-coder-1.3b-base: it balances file size and quality well. Here it is a 0.9 GB file.

The Q8_0 file is 1.4 GB, about 1.6 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 Q2_K at 0.6 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

Architecturellama
Parameters1.35B
Layers24
Trained context16,384 tokens
KV cache (fp16)192 KB per token

Source

Quantized byTheBloke
FamilyDeepSeek
Licenseother
Downloads (HF)6,576
Last updated2023-11-05

Frequently asked questions about deepseek-ai_deepseek-coder-1.3b-base

How much VRAM does deepseek-ai_deepseek-coder-1.3b-base need?

About 3.0 GB at Q4_K_M with an 8K context window. That is the 0.9 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-coder-1.3b-base on an 8 GB GPU?

Yes, with Q8_0: the 1.4 GB file needs about 3.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of deepseek-ai_deepseek-coder-1.3b-base GGUF?

It depends on the quant: Q2_K is 0.6 GB, Q3_K_S is 0.7 GB, Q3_K_M is 0.7 GB, Q3_K_L is 0.7 GB, Q4_0 is 0.8 GB, Q4_K_S is 0.8 GB and 6 more.

What context length does deepseek-ai_deepseek-coder-1.3b-base support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 1.6 GB at 8K and 3.2 GB at 16K.

Where can I download deepseek-ai_deepseek-coder-1.3b-base GGUF?

The files are on Hugging Face in the TheBloke/deepseek-coder-1.3b-base-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-coder-1.3b-base use?

Hugging Face lists the license as other. 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 Coder 1.3B Base on 8 GB VRAM?

Yes, using Q4_K_M or Q5_K_M quantisations, which require approximately 3 GB of VRAM at 8K context.

Does this model support image inputs?

No, DeepSeek Coder 1.3B Base is a text‑only model with no vision capabilities.

Is the model suitable for commercial use?

Yes, the model is licensed under MIT and allows commercial deployment.

Other GGUFs of deepseek-coder-1.3b-base

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More DeepSeek models

All DeepSeek →

Other tiny models

All tiny models →