Gemma 2 Llama Swallow 9b Pt 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 24 quants, from 2.4 GB (IQ1_S) to 7.6 GB (Q6_K).
Gemma 2 Llama Swallow 9b Pt v0.1 – 9.24B parameter Japanese/English LLM
Gemma 2 Llama Swallow 9b Pt v0.1 is a 9.24B parameter model built on the Gemma-2 architecture. It supports Japanese and English languages and was trained on 200 billion tokens from Japanese web corpus, Wikipedia, and coding content. The model is available in multiple GGUF quantizations.
Good at
- Japanese language tasks
- English language tasks
- Instruction‑tuned Japanese content
Limits
- No vision support
- Requires 8 k context for memory estimates
- License is gemma
Best for
- Japanese text generation
- English text generation
- Instruction‑based Japanese queries
Who it’s for. Developers and researchers needing a Japanese‑capable LLM with English support. The model is suitable for applications that can run on a GPU with at least 8 GB VRAM for the smallest quant.
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 → | |
| IQ4_NL | 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 → | |
| Q4_1 | 6.0 GB | 9.3 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 (2.38 GB, 5.7 GB memory at 8k context) or IQ1_M (2.55 GB, 5.9 GB). For 12 GB VRAM use IQ2_S (3.21 GB, 6.5 GB) or Q4_K_M (5.76 GB, 9.1 GB). For 24 GB VRAM use Q5_K_M (6.65 GB, 10 GB) or Q6_K (7.59 GB, 10.9 GB). Estimates are approximate.
What GPU do you need for Gemma 2 Llama Swallow 9b Pt 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 Gemma 2 Llama Swallow 9b Pt v0.1 quant should you choose?
Q4_K_M is the usual starting point for Gemma 2 Llama Swallow 9b Pt 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
Frequently asked questions about Gemma 2 Llama Swallow 9b Pt v0.1
How much VRAM does Gemma 2 Llama Swallow 9b Pt 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 Gemma 2 Llama Swallow 9b Pt 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 Gemma 2 Llama Swallow 9b Pt 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 18 more.
What context length does Gemma 2 Llama Swallow 9b Pt 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 Gemma 2 Llama Swallow 9b Pt v0.1 GGUF?
The files are on Hugging Face in the mradermacher/Gemma-2-Llama-Swallow-9b-pt-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 Gemma 2 Llama Swallow 9b Pt 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, use IQ1_S or IQ1_M quantizations which fit within 8 GB VRAM and use about 5.7–5.9 GB memory at 8k context.
Does this model support vision tasks?
No, the model does not have vision capabilities.
What context length is supported?
The model was trained with 8192 tokens and supports up to that context length.