GE

GemmaX2 28 9B v0.1

GemmaGGUF by mradermacherUpdated 2025-02-24
Download on Hugging Face
Parameters9.24B
Context8K
Layers42
Architecturegemma2
Smallest quant3.8 GB
Quick answer

GemmaX2 28 9B v0.1 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 13 quants, from 3.8 GB (Q2_K) to 18.5 GB (F16).

GemmaX2 28 9B v0.1 – 9.24B parameter multilingual translation model

GemmaX2 28 9B v0.1 is a 9.24B parameter LLM fine‑tuned for translation across 28 languages. It builds on Gemma2‑9B and uses 8192 token context. The model is available in multiple GGUF quantizations.

Good at

  • Multilingual translation in 28 supported languages
  • Fine‑tuned instruction following
  • Large context handling

Limits

  • Only 28 languages supported
  • No vision or audio capabilities
  • License is gemma

Best for

  • Translation pipelines for supported languages
  • Low‑latency inference on edge devices
  • Research on multilingual LLMs

Who it’s for. Developers and researchers needing a compact translation model for the 28 supported languages. The model is suitable for applications that require efficient inference on limited GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.8 GB 7.1 GB
Fits Get file →
Q3_K_S4.3 GB 7.7 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_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 →
Q8_09.8 GB 13.1 GB
Too big Get file →
F1618.5 GB 21.8 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (5.76 GB file, 9.1 GB memory). For 12 GB VRAM, Q5_K_M (6.65 GB file, 10 GB memory) is suitable. For 16 GB VRAM, Q6_K (7.59 GB file, 10.9 GB memory) provides a good balance between size and quality.

What GPU do you need for GemmaX2 28 9B 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: the best quant that fits is Q3_K_S (4.3 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (7.6 GB file, about 10.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.8 GB file, about 13.1 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (18.5 GB file, about 21.8 GB in use).

Which GemmaX2 28 9B v0.1 quant should you choose?

Q4_K_M is the usual starting point for GemmaX2 28 9B v0.1: it balances file size and quality well. Here it is a 5.8 GB file.

The Q8_0 file is 9.8 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 3.8 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)427
Last updated2025-02-24

Frequently asked questions about GemmaX2 28 9B v0.1

How much VRAM does GemmaX2 28 9B v0.1 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 v0.1 on an 8 GB GPU?

Yes, with Q3_K_S: the 4.3 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of GemmaX2 28 9B v0.1 GGUF?

It depends on the quant: Q2_K is 3.8 GB, Q3_K_S is 4.3 GB, Q3_K_M is 4.8 GB, Q3_K_L is 5.1 GB, IQ4_XS is 5.2 GB, Q4_0 is 5.4 GB and 7 more.

What context length does GemmaX2 28 9B v0.1 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 v0.1 GGUF?

The files are on Hugging Face in the mradermacher/GemmaX2-28-9B-v0.1-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 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.

Can I run GemmaX2 28 9B v0.1 on 8 GB VRAM?

Yes, the Q4_K_M quantization requires approximately 9.1 GB memory at 8k context, which fits in 8 GB VRAM with some overhead.

Does the model support languages beyond the 28 listed?

No, the model only supports the 28 languages specified and does not guarantee strong performance for others.

What is the context length of this model?

The trained context length is 8192 tokens.

Other GGUFs of GemmaX2-28-9B-v0.1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Gemma models

All Gemma →

Other small models

All small models →