my fusion v1 needs about 6.6 GB of memory at F16 (a 5.2 GB file) with an 8K context window, so it fits on a 8 GB GPU.
2.61B‑parameter Gemma2 model in Fusion family
my fusion v1 is a 2.61 billion parameter Gemma2 architecture model. It was quantized to F16 and supports a 8192 token context window. No additional license or language metadata is provided.
Good at
- Large context handling
- F16 quantization for efficient inference
- Gemma2 architecture
Limits
- No vision support
- No license information
- Limited language metadata
Best for
- Chat applications needing 8k context
- Fine‑tuning on custom data
- Inference on GPUs with 8 GB VRAM
Who it’s for. Developers and researchers who need a Gemma2‑based model with a large context window and who can work with an F16 quantized file. The model is suitable for those who can manage the memory requirements and do not need vision or specific licensing guarantees.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 5.2 GB | 6.6 GB | Fits | Get file → |
The F16 quantized file is 5.24 GB and requires approximately 6.6 GB of VRAM at 8 k context. This is suitable for GPUs with 8 GB or more VRAM. No other quantizations are available for this model.
What GPU do you need for my fusion v1?
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 F16 (5.2 GB file, about 6.6 GB in use).
Which my fusion v1 quant should you choose?
F16 (5.2 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about my fusion v1
How much VRAM does my fusion v1 need?
About 6.6 GB at F16 with an 8K context window. That is the 5.2 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 my fusion v1 on an 8 GB GPU?
Yes, with F16: the 5.2 GB file needs about 6.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of my fusion v1 GGUF?
It depends on the quant: F16 is 5.2 GB.
What context length does my fusion v1 support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.9 GB at 8K and 0.9 GB at 8K.
Where can I download my fusion v1 GGUF?
The files are on Hugging Face in the David-kim/my-fusion-v1 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run this model on a GPU with 8 GB VRAM?
Yes, the F16 quantized file requires about 6.6 GB of VRAM at 8 k context, which fits within an 8 GB GPU.
What context length does this model support?
It supports a 8192 token context window.
Is there a license for this model?
No license information is provided in the model card.