DE

Deepseek Paraphrase

DeepSeekGGUF by mradermacherUpdated 2025-07-11
Download on Hugging Face
Parameters7.62B
Context128K
Layers28
Architectureqwen2
Smallest quant1.9 GB
Quick answer

Deepseek Paraphrase needs about 5.7 GB of memory at Q4_K_M (a 4.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 24 quants, from 1.9 GB (IQ1_S) to 6.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

Deepseek Paraphrase – a 7.62B Qwen2 model fine‑tuned for high‑quality paraphrasing

Deepseek Paraphrase is a 7.62B Qwen2 model fine‑tuned with LoRA for paraphrase generation. It is trained on multi‑domain text and the Quora paraphrase dataset. The model is released under the MIT license.

Good at

  • High‑quality paraphrasing
  • Semantic preservation
  • Lexical diversity

Limits

  • No vision support
  • Requires 8 k context for estimates
  • Large VRAM for higher quants

Best for

  • Paraphrasing academic text
  • Rewriting technical documentation
  • Generating alternate phrasings for content

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

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.9 GB 2.9 GB
Fits Get file →
IQ1_M2.0 GB 3.0 GB
Fits Get file →
IQ2_XXS2.3 GB 3.2 GB
Fits Get file →
IQ2_XS2.5 GB 3.4 GB
Fits Get file →
IQ2_S2.6 GB 3.6 GB
Fits Get file →
IQ2_M2.8 GB 3.8 GB
Fits Get file →
Q2_K_S2.8 GB 3.8 GB
Fits Get file →
Q2_K3.0 GB 4.0 GB
Fits Get file →
IQ3_XXS3.1 GB 4.1 GB
Fits Get file →
IQ3_XS3.3 GB 4.3 GB
Fits Get file →
Q3_K_S3.5 GB 4.5 GB
Fits Get file →
IQ3_S3.5 GB 4.5 GB
Fits Get file →
IQ3_M3.6 GB 4.5 GB
Fits Get file →
Q3_K_M3.8 GB 4.8 GB
Fits Get file →
Q3_K_L4.1 GB 5.1 GB
Fits Get file →
IQ4_XS4.2 GB 5.2 GB
Fits Get file →
IQ4_NL4.4 GB 5.4 GB
Fits Get file →
Q4_04.4 GB 5.4 GB
Fits Get file →
Q4_K_S4.5 GB 5.4 GB
Fits Get file →
Q4_K_M4.7 GB 5.7 GB
Fits Get file →
Q4_14.9 GB 5.8 GB
Fits Get file →
Q5_K_S5.3 GB 6.3 GB
Fits Get file →
Q5_K_M5.4 GB 6.4 GB
Fits Get file →
Q6_K6.3 GB 7.2 GB
Tight Get file →

For 8 GB VRAM, use IQ1_S (1.9 GB) or IQ1_M (2.04 GB). For 12 GB VRAM, IQ2_S (2.6 GB) or Q2_K (3.02 GB) are good options. For 24 GB VRAM, Q4_K_M (4.68 GB) or Q5_K_M (5.44 GB) provide higher quality. Memory estimates are approximate.

What GPU do you need for Deepseek Paraphrase?

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 Q2_K (3.0 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_1 (4.9 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.3 GB file, about 7.2 GB in use).

Which Deepseek Paraphrase quant should you choose?

Q4_K_M is the usual starting point for Deepseek Paraphrase: it balances file size and quality well. Here it is a 4.7 GB file.

If memory is tight, the smallest file is IQ1_S at 1.9 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
Parameters7.62B
Layers28
Trained context131,072 tokens
KV cache (fp16)56 KB per token

Source

Quantized bymradermacher
FamilyDeepSeek
Licensemit
Downloads (HF)654
Last updated2025-07-11

Frequently asked questions about Deepseek Paraphrase

How much VRAM does Deepseek Paraphrase need?

About 5.7 GB at Q4_K_M with an 8K context window. That is the 4.7 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 Paraphrase on an 8 GB GPU?

Yes, with Q6_K: the 6.3 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Deepseek Paraphrase GGUF?

It depends on the quant: IQ1_S is 1.9 GB, IQ1_M is 2.0 GB, IQ2_XXS is 2.3 GB, IQ2_XS is 2.5 GB, IQ2_S is 2.6 GB, IQ2_M is 2.8 GB and 18 more.

What context length does Deepseek Paraphrase support?

The GGUF header lists a trained context length of 131,072 tokens (128K). 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 Paraphrase GGUF?

The files are on Hugging Face in the mradermacher/deepseek-paraphrase-i1-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 Paraphrase 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 Deepseek Paraphrase on 8 GB VRAM?

Yes, use the IQ1_S or IQ1_M quant, which are 1.9 GB and 2.04 GB respectively.

Does this model support image inputs?

No, the model only handles text.

Other GGUFs of deepseek-paraphrase

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More DeepSeek models

All DeepSeek →

Other small models

All small models →