new f16 model needs about 3.2 GB of memory at F16 (a 2.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.1 GB.
new f16 model is a 1.24B-parameter New model in GGUF format, quantized by plays1. Its trained context length is 128K tokens. The repository has 1 quant file, from 2.5 GB (F16) to 2.5 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 2.5 GB | 3.2 GB | Fits | Get file → |
What GPU do you need for new f16 model?
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 F16 (2.5 GB file, about 3.2 GB in use).
Which new f16 model quant should you choose?
F16 (2.5 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 new f16 model
How much VRAM does new f16 model need?
About 3.2 GB at F16 with an 8K context window. That is the 2.5 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 new f16 model on an 8 GB GPU?
Yes, with F16: the 2.5 GB file needs about 3.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of new f16 model GGUF?
It depends on the quant: F16 is 2.5 GB.
What context length does new f16 model support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.1 GB at 32K.
Where can I download new f16 model GGUF?
The files are on Hugging Face in the plays1/new_f16_model repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.