DE

unsloth finetune

DeepSeekGGUF by see-kUpdated 2026-06-18
Download on Hugging Face
Parameters2.93B
Context8K
Layers—
Architecturedeepseek2-ocr
Smallest quant5.9 GB
Quick answer

unsloth finetune needs about 7.1 GB of memory at F16 (a 5.9 GB file) with an 8K context window, so it fits on a 8 GB GPU.

unsloth finetune is a 2.93B-parameter DeepSeek model in GGUF format, quantized by see-k. Its trained context length is 8K tokens. The repository has 1 quant file, from 5.9 GB (F16) to 5.9 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F165.9 GB 7.1 GB
Fits Get file →

What GPU do you need for unsloth finetune?

These figures add the file size, an fp16 KV cache at an 8K context window 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 F16 (5.9 GB file, about 7.1 GB in use).

Which unsloth finetune quant should you choose?

F16 (5.9 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedeepseek2-ocr
Parameters2.93B
Trained context8,192 tokens

Source

Quantized bysee-k
FamilyDeepSeek
Licenseapache-2.0
Downloads (HF)76
Last updated2026-06-18

Frequently asked questions about unsloth finetune

How much VRAM does unsloth finetune need?

About 7.1 GB at F16 with an 8K context window. That is the 5.9 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 unsloth finetune on an 8 GB GPU?

Yes, with F16: the 5.9 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of unsloth finetune GGUF?

It depends on the quant: F16 is 5.9 GB.

What context length does unsloth finetune support?

The GGUF header lists a trained context length of 8,192 tokens (8K).

Where can I download unsloth finetune GGUF?

The files are on Hugging Face in the see-k/unsloth_finetune repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does unsloth finetune use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of DeepSeek-OCR

Similar models

Browse all →

More DeepSeek models

All DeepSeek →

Other tiny models

All tiny models →