GE

GemmaX2 28 9B Pretrain

GemmaGGUF by mradermacherUpdated 2025-02-25
Download on Hugging Face
Parameters9.24B
Context8K
Layers42
Architecturegemma2
Smallest quant2.4 GB
Quick answer

GemmaX2 28 9B Pretrain needs about 9.1 GB of memory at Q4_K_M (a 5.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 2.4 GB (IQ1_S) to 7.6 GB (Q6_K).

GemmaX2 28 9B Pretrain – 9.24B parameter multilingual language model

GemmaX2 28 9B Pretrain is a 9.24B parameter model built on Gemma2 architecture. It was continually pretrained on 56 billion tokens across 28 languages. The model supports a 8192 token context window.

Good at

  • Multilingual text generation
  • Large context handling
  • High‑quality language modeling

Limits

  • No vision support
  • Not a translation model
  • Requires 8 k context for memory estimates

Best for

  • Chatbots needing multilingual support
  • Research on language modeling
  • Content creation in multiple languages

Who it’s for. Developers and researchers who need a large, multilingual language model without vision capabilities. The model is suitable for applications that require extensive context handling and high‑quality text generation across many languages.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.4 GB 5.7 GB
Fits Get file →
IQ1_M2.5 GB 5.9 GB
Fits Get file →
IQ2_XXS2.8 GB 6.1 GB
Fits Get file →
IQ2_XS3.1 GB 6.4 GB
Fits Get file →
IQ2_S3.2 GB 6.5 GB
Fits Get file →
IQ2_M3.4 GB 6.8 GB
Fits Get file →
Q2_K_S3.6 GB 6.9 GB
Fits Get file →
IQ3_XXS3.8 GB 7.1 GB
Fits Get file →
Q2_K3.8 GB 7.1 GB
Fits Get file →
IQ3_XS4.1 GB 7.5 GB
Tight Get file →
IQ3_S4.3 GB 7.7 GB
Tight Get file →
Q3_K_S4.3 GB 7.7 GB
Tight Get file →
IQ3_M4.5 GB 7.8 GB
Tight Get file →
Q3_K_M4.8 GB 8.1 GB
Too big Get file →
Q3_K_L5.1 GB 8.5 GB
Too big Get file →
IQ4_XS5.2 GB 8.5 GB
Too big Get file →
Q4_05.4 GB 8.8 GB
Too big Get file →
Q4_05.4 GB 8.8 GB
Too big Get file →
Q4_05.4 GB 8.8 GB
Too big Get file →
Q4_05.5 GB 8.8 GB
Too big Get file →
Q4_K_S5.5 GB 8.8 GB
Too big Get file →
Q4_K_M5.8 GB 9.1 GB
Too big Get file →
Q5_K_S6.5 GB 9.8 GB
Too big Get file →
Q5_K_M6.6 GB 10.0 GB
Too big Get file →
Q6_K7.6 GB 10.9 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (2.38 GB, 5.7 GB memory at 8 k context) or IQ1_M (2.55 GB, 5.9 GB). For 16 GB VRAM, Q4_K_M (5.76 GB, 9.1 GB) or Q5_K_M (6.65 GB, 10 GB) are suitable. Higher quants provide more accuracy but need more memory.

What GPU do you need for GemmaX2 28 9B Pretrain?

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: the best quant that fits is IQ1_M (2.5 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ3_M (4.5 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (7.6 GB file, about 10.9 GB in use).

Which GemmaX2 28 9B Pretrain quant should you choose?

Q4_K_M is the usual starting point for GemmaX2 28 9B Pretrain: it balances file size and quality well. Here it is a 5.8 GB file.

If memory is tight, the smallest file is IQ1_S at 2.4 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

Architecturegemma2
Parameters9.24B
Layers42
Trained context8,192 tokens
KV cache (fp16)336 KB per token

Source

Quantized bymradermacher
FamilyGemma
Licensegemma
Downloads (HF)619
Last updated2025-02-25

Frequently asked questions about GemmaX2 28 9B Pretrain

How much VRAM does GemmaX2 28 9B Pretrain need?

About 9.1 GB at Q4_K_M with an 8K context window. That is the 5.8 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 GemmaX2 28 9B Pretrain on an 8 GB GPU?

Yes, with IQ3_M: the 4.5 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of GemmaX2 28 9B Pretrain GGUF?

It depends on the quant: IQ1_S is 2.4 GB, IQ1_M is 2.5 GB, IQ2_XXS is 2.8 GB, IQ2_XS is 3.1 GB, IQ2_S is 3.2 GB, IQ2_M is 3.4 GB and 19 more.

What context length does GemmaX2 28 9B Pretrain support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.8 GB at 8K and 2.8 GB at 8K.

Where can I download GemmaX2 28 9B Pretrain GGUF?

The files are on Hugging Face in the mradermacher/GemmaX2-28-9B-Pretrain-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 GemmaX2 28 9B Pretrain 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.

Can I run this model on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quantizations; they fit within 8 GB VRAM and use about 5.7–5.9 GB memory at 8 k context.

Does this model support image input?

No, the model has no vision capabilities.

Is this model suitable for translation tasks?

No, GemmaX2 28 9B Pretrain is not a translation model.

Other GGUFs of GemmaX2-28-9B-Pretrain

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Gemma models

All Gemma →

Other small models

All small models →