DE

Deepseek Coder V2 Lite 13B Instruct Sft Math7K

DeepSeekGGUF by mradermacherUpdated 2025-12-09
Download on Hugging Face
Parameters15.7B
Context160K
Layers27
Architecturedeepseek2
Smallest quant0.0 GB
Quick answer

Deepseek Coder V2 Lite 13B Instruct Sft Math7K needs about 11.3 GB of memory at Q4_K_M (a 10.4 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 14.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

Deepseek Coder V2 Lite 13B Instruct Sft Math7K – a 15.7B parameter coding model

Deepseek Coder V2 Lite 13B Instruct Sft Math7K is a 15.7B parameter model fine‑tuned for coding tasks. It supports a context length of 163840 tokens and is available in multiple GGUF quantizations. The model is part of the DeepSeek family and is hosted on Hugging Face.

Good at

  • Coding tasks
  • Large context handling
  • Fine‑tuned for math code

Limits

  • No vision support
  • License not specified
  • Requires 8k context for memory estimates

Best for

  • Generating code snippets
  • Debugging assistance
  • Code completion in IDEs

Who it’s for. Developers and researchers needing a lightweight coding model with large context. The model is suitable for local inference using llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.0 GB
Fits Get file →
IQ1_S5.0 GB 6.0 GB
Fits Get file →
IQ1_M5.2 GB 6.2 GB
Fits Get file →
IQ2_XXS5.6 GB 6.6 GB
Fits Get file →
IQ2_XS6.0 GB 7.0 GB
Fits Get file →
IQ2_S6.0 GB 7.0 GB
Fits Get file →
IQ2_M6.3 GB 7.3 GB
Tight Get file →
Q2_K6.4 GB 7.4 GB
Tight Get file →
Q2_K_S6.5 GB 7.4 GB
Tight Get file →
IQ3_XXS7.0 GB 8.0 GB
Tight Get file →
IQ3_XS7.1 GB 8.1 GB
Too big Get file →
IQ3_S7.5 GB 8.5 GB
Too big Get file →
Q3_K_S7.5 GB 8.5 GB
Too big Get file →
IQ3_M7.6 GB 8.5 GB
Too big Get file →
Q3_K_M8.1 GB 9.1 GB
Too big Get file →
Q3_K_L8.5 GB 9.4 GB
Too big Get file →
IQ4_XS8.6 GB 9.6 GB
Too big Get file →
IQ4_NL8.9 GB 9.9 GB
Too big Get file →
Q4_08.9 GB 9.9 GB
Too big Get file →
Q4_K_S9.5 GB 10.5 GB
Too big Get file →
Q4_19.9 GB 10.9 GB
Too big Get file →
Q4_K_M10.4 GB 11.3 GB
Too big Get file →
Q5_K_S11.1 GB 12.1 GB
Too big Get file →
Q5_K_M11.9 GB 12.8 GB
Too big Get file →
Q6_K14.1 GB 15.1 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (10.37 GB file, 11.3 GB memory at 8k context). For 12 GB VRAM, Q5_K_M (11.85 GB file, 12.8 GB memory). For 16 GB VRAM, Q6_K (14.07 GB file, 15.1 GB memory). Estimates are approximate.

What GPU do you need for Deepseek Coder V2 Lite 13B Instruct Sft Math7K?

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 (0.0 GB file, about 1.0 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ1_S (5.0 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ3_XXS (7.0 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_M (10.4 GB file, about 11.3 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (14.1 GB file, about 15.1 GB in use).

Which Deepseek Coder V2 Lite 13B Instruct Sft Math7K quant should you choose?

Q4_K_M is the usual starting point for Deepseek Coder V2 Lite 13B Instruct Sft Math7K: it balances file size and quality well. Here it is a 10.4 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 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
Parameters15.7B (approximate, mixture of experts)
Layers27
Trained context163,840 tokens
KV cache (fp16)57 KB per token

Frequently asked questions about Deepseek Coder V2 Lite 13B Instruct Sft Math7K

How much VRAM does Deepseek Coder V2 Lite 13B Instruct Sft Math7K need?

About 11.3 GB at Q4_K_M with an 8K context window. That is the 10.4 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 Coder V2 Lite 13B Instruct Sft Math7K on an 8 GB GPU?

Yes, with IQ3_XXS: the 7.0 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Deepseek Coder V2 Lite 13B Instruct Sft Math7K GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 5.0 GB, IQ1_M is 5.2 GB, IQ2_XXS is 5.6 GB, IQ2_XS is 6.0 GB, IQ2_S is 6.0 GB and 19 more.

What context length does Deepseek Coder V2 Lite 13B Instruct Sft Math7K support?

The GGUF header lists a trained context length of 163,840 tokens (160K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download Deepseek Coder V2 Lite 13B Instruct Sft Math7K GGUF?

The files are on Hugging Face in the mradermacher/Deepseek-Coder-V2-Lite-13B-Instruct-sft-math7k-i1-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 this model on 8 GB VRAM?

Use the Q4_K_M quant, which requires about 11.3 GB of VRAM at 8k context.

Does this model support vision tasks?

No, the model is only for coding and text generation.

What is the context length of this model?

The model supports 163840 tokens of context.

Other GGUFs of Deepseek-Coder-V2-Lite-13B-Instruct-sft-math7k

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More DeepSeek models

All DeepSeek →

Other medium models

All medium models →