GemPT 26B A4B needs about 1.2 GB of memory at BF16 (a 0.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.6 GB (BF16) to 26.9 GB (Q8_0).
GemPT 26B A4B is a 25.2B-parameter Gempt model in GGUF format, quantized by Entity-27th. Its trained context length is 256K tokens. The repository has 2 quant files, from 0.6 GB (BF16) to 26.9 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 0.6 GB | 1.2 GB | Fits | Get file → | |
| Q8_0 | 26.9 GB | 30.6 GB | Too big | Get file → |
What GPU do you need for GemPT 26B A4B?
These figures add the file size, an fp16 KV cache at an 8K context window 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 BF16 (0.6 GB file, about 1.2 GB in use).
- 6 GB VRAM: the best quant that fits is BF16 (0.6 GB file, about 1.2 GB in use).
- 8 GB VRAM: the best quant that fits is BF16 (0.6 GB file, about 1.2 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (0.6 GB file, about 1.2 GB in use).
- 16 GB VRAM: the best quant that fits is BF16 (0.6 GB file, about 1.2 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (0.6 GB file, about 1.2 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (26.9 GB file, about 30.6 GB in use).
Which GemPT 26B A4B quant should you choose?
BF16 (0.6 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 GemPT 26B A4B
How much VRAM does GemPT 26B A4B need?
About 1.2 GB at BF16 with an 8K context window. That is the 0.6 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 GemPT 26B A4B on an 8 GB GPU?
Yes, with BF16: the 0.6 GB file needs about 1.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of GemPT 26B A4B GGUF?
It depends on the quant: BF16 is 0.6 GB, Q8_0 is 26.9 GB.
What context length does GemPT 26B A4B support?
The GGUF header lists a trained context length of 262,144 tokens (256K).
Where can I download GemPT 26B A4B GGUF?
The files are on Hugging Face in the Entity-27th/GemPT-26B-A4B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.