Refact 1_6 Base needs about 1.5 GB of memory at Q4_K_M (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU.
Refact 1_6 Base is a 1.59B-parameter Refact model in GGUF format, quantized by panos345. Its trained context length is 4K tokens. The repository has 1 quant file, from 1.0 GB (Q4_K_M) to 1.0 GB (Q4_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.0 GB | 1.5 GB | Fits | Get file → |
What GPU do you need for Refact 1_6 Base?
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 Q4_K_M (1.0 GB file, about 1.5 GB in use).
Which Refact 1_6 Base quant should you choose?
Q4_K_M is the usual starting point for Refact 1_6 Base: it balances file size and quality well. Here it is a 1.0 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Refact 1_6 Base
How much VRAM does Refact 1_6 Base need?
About 1.5 GB at Q4_K_M with an 8K context window. That is the 1.0 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 Refact 1_6 Base on an 8 GB GPU?
Yes, with Q4_K_M: the 1.0 GB file needs about 1.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Refact 1_6 Base GGUF?
It depends on the quant: Q4_K_M is 1.0 GB.
What context length does Refact 1_6 Base support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 4K.
Where can I download Refact 1_6 Base GGUF?
The files are on Hugging Face in the panos345/Refact-1_6-base-Q4_K_M-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 Refact 1_6 Base use?
Hugging Face lists the license as bigscience-openrail-m. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.