LL

Gemma 2 Llama Swallow 9b it v0.1

LlamaGGUF by marceloneUpdated 2025-10-18
Download on Hugging Face
Parameters9.24B
Context16K
Layers42
Architecturegemma2
Smallest quant6.5 GB
Quick answer

Gemma 2 Llama Swallow 9b it v0.1 needs about 9.8 GB of memory at Q4_0 (a 6.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 6.5 GB (Q4_0) to 6.5 GB (Q4_0).

Gemma 2 Llama Swallow 9b it v0.1 is a 9.24B-parameter Llama model in GGUF format, quantized by marcelone. Its trained context length is 16K tokens. The repository has 2 quant files, from 6.5 GB (Q4_0) to 6.5 GB (Q4_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_06.5 GB 9.8 GB
Too big Get file →
Q4_06.5 GB 9.8 GB
Too big Get file →

What GPU do you need for Gemma 2 Llama Swallow 9b it v0.1?

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 Q4_0 (6.5 GB file, about 9.8 GB in use).

Which Gemma 2 Llama Swallow 9b it v0.1 quant should you choose?

Q4_0 (6.5 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma2
Parameters9.24B
Layers42
Trained context16,384 tokens
KV cache (fp16)336 KB per token

Source

Quantized bymarcelone
FamilyLlama
Licensegemma
Downloads (HF)35
Last updated2025-10-18

Frequently asked questions about Gemma 2 Llama Swallow 9b it v0.1

How much VRAM does Gemma 2 Llama Swallow 9b it v0.1 need?

About 9.8 GB at Q4_0 with an 8K context window. That is the 6.5 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 2 Llama Swallow 9b it v0.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Gemma 2 Llama Swallow 9b it v0.1 GGUF?

It depends on the quant: Q4_0 is 6.5 GB, Q4_0 is 6.5 GB.

What context length does Gemma 2 Llama Swallow 9b it v0.1 support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 2.8 GB at 8K and 5.6 GB at 16K.

Where can I download Gemma 2 Llama Swallow 9b it v0.1 GGUF?

The files are on Hugging Face in the marcelone/Gemma-2-Llama-Swallow-9b-it-v0.1 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Gemma 2 Llama Swallow 9b it v0.1 use?

Hugging Face lists the license as gemma. 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 Gemma-2-Llama-Swallow-9b-it-v0.1

Similar models

Browse all →

More from marcelone

All by marcelone →

More Llama models

All Llama →

Other small models

All small models →