DE

DeepSeek-R1-Distill-Qwen-14B

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

DeepSeek-R1-Distill-Qwen-14B needs about 11.1 GB of memory at Q4_K_M (a 9.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 29 quants, from 4.3 GB (IQ2_XXS) to 29.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

14.8B Qwen2 model distilled for efficient inference

DeepSeek‑R1‑Distill‑Qwen‑14B is a 14.8B‑parameter Qwen2 architecture model. It supports reasoning and tool usage. The model is released under the MIT license and trained on 131072 context tokens.

Good at

  • Reasoning
  • Tool usage
  • Large context handling

Limits

  • No vision support
  • Requires 8k context for estimates
  • No explicit language list

Best for

  • Chatbot back‑end
  • Code generation
  • Data analysis queries

Who it’s for. Developers building conversational agents or code assistants who need a large‑parameter model with reasoning capabilities. The MIT license allows free use in commercial and non‑commercial projects.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS4.3 GB 6.4 GB
Fits Get file →
IQ2_XS4.7 GB 6.8 GB
Fits Get file →
IQ2_M5.4 GB 7.5 GB
Tight Get file →
Q2_K_S5.4 GB 7.5 GB
Tight Get file →
IQ3_XXS5.9 GB 8.1 GB
Too big Get file →
IQ3_XS6.4 GB 8.5 GB
Too big Get file →
Q3_K_S6.7 GB 8.8 GB
Too big Get file →
IQ3_S6.7 GB 8.8 GB
Too big Get file →
IQ3_M6.9 GB 9.0 GB
Too big Get file →
Q3_K_M7.3 GB 9.4 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_S8.6 GB 10.7 GB
Too big Get file →
Q4_K_M9.0 GB 11.1 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_S10.3 GB 12.4 GB
Too big Get file →
Q5_K_M10.5 GB 12.6 GB
Too big Get file →
BF1611.0 GB 13.1 GB
Too big Get file →
F1611.0 GB 13.1 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 →
BF1614.0 GB 16.1 GB
Too big Get file →
F1614.0 GB 16.1 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 IQ2_XXS (4.31 GB, 6.4 GB memory) or IQ2_XS (4.7 GB, 6.8 GB memory). For 12 GB VRAM, Q4_0 (8.32 GB, 10.4 GB memory) or Q4_K_S (8.57 GB, 10.7 GB memory) are suitable. For 16 GB VRAM, Q5_0 (10.16 GB, 12.3 GB memory) or Q6_K_M (12.12 GB, 14.2 GB memory) provide higher precision.

What GPU do you need for DeepSeek-R1-Distill-Qwen-14B?

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 Q2_K_S (5.4 GB file, about 7.5 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 DeepSeek-R1-Distill-Qwen-14B quant should you choose?

Q4_K_M is the usual starting point for DeepSeek-R1-Distill-Qwen-14B: it balances file size and quality well. Here it is a 9.0 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 IQ2_XXS 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)763
Last updated2025-09-24

Frequently asked questions about DeepSeek-R1-Distill-Qwen-14B

How much VRAM does DeepSeek-R1-Distill-Qwen-14B need?

About 11.1 GB at Q4_K_M with an 8K context window. That is the 9.0 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-R1-Distill-Qwen-14B on an 8 GB GPU?

Yes, with Q2_K_S: the 5.4 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of DeepSeek-R1-Distill-Qwen-14B GGUF?

It depends on the quant: IQ2_XXS is 4.3 GB, IQ2_XS is 4.7 GB, IQ2_M is 5.4 GB, Q2_K_S is 5.4 GB, IQ3_XXS is 5.9 GB, IQ3_XS is 6.4 GB and 23 more.

What context length does DeepSeek-R1-Distill-Qwen-14B 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 DeepSeek-R1-Distill-Qwen-14B GGUF?

The files are on Hugging Face in the Mungert/DeepSeek-R1-Distill-Qwen-14B-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-R1-Distill-Qwen-14B 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 this model on 8 GB VRAM?

Yes, using IQ2_XXS or IQ2_XS quantizations keeps memory usage below 8 GB.

Does the model support vision tasks?

No, the model has no vision capabilities.

What precision is best for CPU inference?

Lower‑bit quantizations like Q4_K or IQ4_XS are recommended for CPU and low‑VRAM setups.

Similar models

Browse all →

More from Mungert

All by Mungert →

More DeepSeek models

All DeepSeek →

Other medium models

All medium models →