MITI Tax Gemma Instruct Finetune 1.0 needs about 3.3 GB of memory at its main file (a 2.7 GB file) with an 8K context window, so it fits on a 4 GB GPU.
MITI Tax Gemma Instruct Finetune 1.0 is a 2.51B-parameter Gemma model in GGUF format, quantized by prasadkanche. Its trained context length is 8K tokens. The repository has 1 quant file, from 2.7 GB to 2.7 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 2.7 GB | 3.3 GB | Fits | Get file → |
What GPU do you need for MITI Tax Gemma Instruct Finetune 1.0?
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: the best quant that fits is the main file (2.7 GB file, about 3.3 GB in use).
Specifications
Architecture from the GGUF header
Frequently asked questions about MITI Tax Gemma Instruct Finetune 1.0
How much VRAM does MITI Tax Gemma Instruct Finetune 1.0 need?
About 3.3 GB at its main file with an 8K context window. That is the 2.7 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 MITI Tax Gemma Instruct Finetune 1.0 on an 8 GB GPU?
Yes, with the smaller files: the 2.7 GB file needs about 3.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of MITI Tax Gemma Instruct Finetune 1.0 GGUF?
It depends on the quant: file is 2.7 GB.
What context length does MITI Tax Gemma Instruct Finetune 1.0 support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.2 GB at 8K.
Where can I download MITI Tax Gemma Instruct Finetune 1.0 GGUF?
The files are on Hugging Face in the prasadkanche/MITI-Tax-Gemma-Instruct-Finetune-1.0.gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.