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 25 quants, from 2.4 GB (IQ1_S) to 7.6 GB (Q6_K).
GemmaX2 28 9B v0.1 – a 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 was trained on 56B tokens of monolingual and parallel data and supports a 8192 token context window. The model is available in multiple GGUF quantizations.
Good at
- High‑quality translation in 28 supported languages
- Large context handling up to 8192 tokens
- Efficient inference with GGUF quantizations
Limits
- Only supports the 28 listed languages
- No vision or multimodal capabilities
- License is gemma, not open source
Best for
- Developers building translation services
- Researchers testing multilingual LLMs
- Deployments requiring low‑memory inference
Who it’s for. The model is suitable for developers and researchers who need a multilingual translation engine with a large context window and who can work within the 28 language constraints. It is ideal for applications that can leverage GGUF quantizations for efficient inference.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 2.4 GB | 5.7 GB | Fits | Get file → | |
| IQ1_M | 2.5 GB | 5.9 GB | Fits | Get file → | |
| IQ2_XXS | 2.8 GB | 6.1 GB | Fits | Get file → | |
| IQ2_XS | 3.1 GB | 6.4 GB | Fits | Get file → | |
| IQ2_S | 3.2 GB | 6.5 GB | Fits | Get file → | |
| IQ2_M | 3.4 GB | 6.8 GB | Fits | Get file → | |
| Q2_K_S | 3.6 GB | 6.9 GB | Fits | Get file → | |
| IQ3_XXS | 3.8 GB | 7.1 GB | Fits | Get file → | |
| Q2_K | 3.8 GB | 7.1 GB | Fits | Get file → | |
| IQ3_XS | 4.1 GB | 7.5 GB | Tight | Get file → | |
| IQ3_S | 4.3 GB | 7.7 GB | Tight | Get file → | |
| Q3_K_S | 4.3 GB | 7.7 GB | Tight | Get file → | |
| IQ3_M | 4.5 GB | 7.8 GB | Tight | Get file → | |
| Q3_K_M | 4.8 GB | 8.1 GB | Too big | Get file → | |
| Q3_K_L | 5.1 GB | 8.5 GB | Too big | Get file → | |
| IQ4_XS | 5.2 GB | 8.5 GB | Too big | Get file → | |
| Q4_0 | 5.4 GB | 8.8 GB | Too big | Get file → | |
| Q4_0 | 5.4 GB | 8.8 GB | Too big | Get file → | |
| Q4_0 | 5.4 GB | 8.8 GB | Too big | Get file → | |
| Q4_0 | 5.5 GB | 8.8 GB | Too big | Get file → | |
| Q4_K_S | 5.5 GB | 8.8 GB | Too big | Get file → | |
| Q4_K_M | 5.8 GB | 9.1 GB | Too big | Get file → | |
| Q5_K_S | 6.5 GB | 9.8 GB | Too big | Get file → | |
| Q5_K_M | 6.6 GB | 10.0 GB | Too big | Get file → | |
| Q6_K | 7.6 GB | 10.9 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (file size 2.38 GB, memory 5.7 GB) or IQ1_M (2.55 GB, 5.9 GB). For 12 GB VRAM, IQ2_M (3.43 GB, 6.8 GB) or Q2_K (3.81 GB, 7.1 GB) are suitable. For 16 GB VRAM, Q3_K_M (4.76 GB, 8.1 GB) or Q4_K_M (5.76 GB, 9.1 GB) provide a good balance of size and memory usage.
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: 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 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.
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
Source
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 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 v0.1 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 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-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 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 this model on 8 GB VRAM?
Yes, using IQ1_S or IQ1_M quantizations which require approximately 5.7–5.9 GB of VRAM at 8k context.
Does the model support languages outside the 28 listed?
No, the model only supports the 28 languages specified in its documentation.
What is the context length of this model?
The model supports a context length of 8192 tokens.