DE

gemma 3 12b deepseek r1 distill

DeepSeekGGUF by ykaroutUpdated 2025-05-21
Download on Hugging Face
Parameters12.8B
Context128K
Layers48
Architecturegemma3
Smallest quant7.9 GB
Quick answer

gemma 3 12b deepseek r1 distill needs about 11.6 GB of memory at BF16 (a 7.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.

gemma 3 12b deepseek r1 distill is a 12.8B-parameter DeepSeek model in GGUF format, quantized by ykarout. Its trained context length is 128K tokens. The repository has 1 quant file, from 7.9 GB (BF16) to 7.9 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF167.9 GB 11.6 GB
Too big Get file →

What GPU do you need for gemma 3 12b deepseek r1 distill?

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: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is BF16 (7.9 GB file, about 11.6 GB in use).

Which gemma 3 12b deepseek r1 distill quant should you choose?

BF16 (7.9 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

Architecturegemma3
Parameters12.8B
Layers48
Trained context131,072 tokens
KV cache (fp16)384 KB per token

Source

Quantized byykarout
FamilyDeepSeek
Downloads (HF)57
Last updated2025-05-21

Frequently asked questions about gemma 3 12b deepseek r1 distill

How much VRAM does gemma 3 12b deepseek r1 distill need?

About 11.6 GB at BF16 with an 8K context window. That is the 7.9 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 gemma 3 12b deepseek r1 distill on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of gemma 3 12b deepseek r1 distill GGUF?

It depends on the quant: BF16 is 7.9 GB.

What context length does gemma 3 12b deepseek r1 distill support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.

Where can I download gemma 3 12b deepseek r1 distill GGUF?

The files are on Hugging Face in the ykarout/gemma-3-12b-deepseek-r1-distill-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of gemma-3-12b-deepseek-r1-v2-bf16

Similar models

Browse all →

More from ykarout

All by ykarout →

More DeepSeek models

All DeepSeek →

Other medium models

All medium models →