DE

DeepCoder-14B-Preview

DeepSeekGGUF by MungertUpdated 2025-09-24
Download on Hugging Face
Parameters14.8B
Context128K
Layers48
Architectureqwen2
Smallest quant4.3 GB
Quick answer

DeepCoder-14B-Preview needs about 11.3 GB of memory at Q4_K_M (a 9.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 29 quants, from 4.3 GB (IQ1_S) to 29.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

DeepCoder-14B-Preview: 14.8B‑parameter Qwen2 model focused on coding, reasoning, and tool use

DeepCoder‑14B‑Preview is a 14.8B‑parameter Qwen2 model distilled from DeepSeek‑R1. It supports a 131072‑token context window and is licensed under MIT. The model excels at coding, reasoning, and tool‑based tasks.

Good at

  • Coding tasks
  • Complex reasoning
  • Tool integration

Limits

  • No vision support
  • Requires large VRAM for higher‑bit quantizations
  • License is MIT

Best for

  • Generating code snippets
  • Solving logic puzzles
  • Automating tool workflows

Who it’s for. Developers and researchers who need a large, open‑source model for code generation and reasoning. The model is suitable for local deployment on systems with sufficient VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S4.3 GB 6.4 GB
Fits Get file →
IQ1_M4.5 GB 6.6 GB
Fits Get file →
IQ2_XXS4.9 GB 7.0 GB
Fits Get file →
IQ2_XS5.2 GB 7.3 GB
Tight Get file →
Q2_K_S5.6 GB 7.7 GB
Tight Get file →
IQ2_S5.8 GB 7.9 GB
Tight Get file →
IQ2_M6.1 GB 8.2 GB
Too big Get file →
IQ3_XXS6.1 GB 8.3 GB
Too big Get file →
Q2_K_M6.2 GB 8.3 GB
Too big Get file →
IQ3_XS6.5 GB 8.6 GB
Too big Get file →
Q3_K_S6.8 GB 8.9 GB
Too big Get file →
IQ3_S6.8 GB 8.9 GB
Too big Get file →
IQ3_M7.0 GB 9.1 GB
Too big Get file →
Q3_K_M7.6 GB 9.8 GB
Too big Get file →
IQ4_XS8.1 GB 10.2 GB
Too big Get file →
Q4_08.3 GB 10.4 GB
Too big Get file →
IQ4_NL8.5 GB 10.7 GB
Too big Get file →
Q4_K_S8.8 GB 10.9 GB
Too big Get file →
Q4_K_M9.2 GB 11.3 GB
Too big Get file →
Q4_19.2 GB 11.4 GB
Too big Get file →
Q5_010.2 GB 12.3 GB
Too big Get file →
Q5_K_S10.4 GB 12.5 GB
Too big Get file →
Q5_K_M10.6 GB 12.7 GB
Too big Get file →
Q5_111.1 GB 13.2 GB
Too big Get file →
Q6_K_M12.1 GB 14.2 GB
Too big Get file →
Q8_015.7 GB 17.8 GB
Too big Get file →
BF1617.2 GB 19.3 GB
Too big Get file →
F1617.2 GB 19.3 GB
Too big Get file →
BF1629.5 GB 31.7 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (4.34 GB file, ~6.4 GB memory at 8 k context) or IQ1_M (4.53 GB file, ~6.6 GB memory). If you have 12 GB VRAM, IQ2_XS (5.15 GB file, ~7.3 GB memory) or Q2_K_S (5.57 GB file, ~7.7 GB memory) are good choices. For 16 GB VRAM, Q4_K_M (9.19 GB file, ~11.3 GB memory) or Q5_K_M (10.61 GB file, ~12.7 GB memory) provide higher quality.

What GPU do you need for DeepCoder-14B-Preview?

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: the best quant that fits is IQ2_S (5.8 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_1 (9.2 GB file, about 11.4 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K_M (12.1 GB file, about 14.2 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (17.2 GB file, about 19.3 GB in use).
  • 32 GB VRAM: the best quant that fits is BF16 (29.5 GB file, about 31.7 GB in use).

Which DeepCoder-14B-Preview quant should you choose?

Q4_K_M is the usual starting point for DeepCoder-14B-Preview: it balances file size and quality well. Here it is a 9.2 GB file.

The Q8_0 file is 15.7 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 IQ1_S at 4.3 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

Architectureqwen2
Parameters14.8B
Layers48
Trained context131,072 tokens
KV cache (fp16)192 KB per token

Source

Quantized byMungert
FamilyDeepSeek
Licensemit
Downloads (HF)671
Last updated2025-09-24

Frequently asked questions about DeepCoder-14B-Preview

How much VRAM does DeepCoder-14B-Preview need?

About 11.3 GB at Q4_K_M with an 8K context window. That is the 9.2 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 DeepCoder-14B-Preview on an 8 GB GPU?

Yes, with IQ2_S: the 5.8 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of DeepCoder-14B-Preview GGUF?

It depends on the quant: IQ1_S is 4.3 GB, IQ1_M is 4.5 GB, IQ2_XXS is 4.9 GB, IQ2_XS is 5.2 GB, Q2_K_S is 5.6 GB, IQ2_S is 5.8 GB and 23 more.

What context length does DeepCoder-14B-Preview support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download DeepCoder-14B-Preview GGUF?

The files are on Hugging Face in the Mungert/DeepCoder-14B-Preview-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 DeepCoder-14B-Preview 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 DeepCoder-14B-Preview on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quantizations. They require about 6.4–6.6 GB memory at 8 k context.

Does the model support image input?

No, the model has no vision capabilities.

What license does the model use?

The model is released under the MIT license.

Other GGUFs of DeepSeek-R1-Distill-Qwen-14B

Similar models

Browse all →

More from Mungert

All by Mungert →

More DeepSeek models

All DeepSeek →

Other medium models

All medium models →