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. This repository has 14 quants, from 0.6 GB (Q2_K) to 1.7 GB (Q8_0).
Refact 1 6 base – 1.59B parameter code completion model
Refact 1 6 base is a 1.59B parameter model trained on English code and text. It supports fill‑in‑the‑middle and chat formats. The model is available in multiple GGUF quantizations.
Good at
- Code completion
- Fill‑in‑the‑middle
- Chat in English
Limits
- No vision support
- License is bigscience‑openrail‑m
- No non‑English language support
Best for
- Python code generation
- JavaScript debugging
- Chatbot for coding queries
Who it’s for. Developers and researchers needing a lightweight code assistant. The model is suitable for local inference with llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.6 GB | 1.2 GB | Fits | Get file → | |
| Q3_K_S | 0.7 GB | 1.3 GB | Fits | Get file → | |
| Q3_K_M | 0.8 GB | 1.3 GB | Fits | Get file → | |
| Q3_K_L | 0.9 GB | 1.4 GB | Fits | Get file → | |
| Q4_0 | 0.9 GB | 1.5 GB | Fits | Get file → | |
| Q4_K_S | 0.9 GB | 1.5 GB | Fits | Get file → | |
| Q4_K_M | 1.0 GB | 1.5 GB | Fits | Get file → | |
| Q4_1 | 1.0 GB | 1.5 GB | Fits | Get file → | |
| Q5_0 | 1.1 GB | 1.6 GB | Fits | Get file → | |
| Q5_K_S | 1.1 GB | 1.6 GB | Fits | Get file → | |
| Q5_K_M | 1.1 GB | 1.7 GB | Fits | Get file → | |
| Q5_1 | 1.2 GB | 1.7 GB | Fits | Get file → | |
| Q6_K | 1.3 GB | 1.8 GB | Fits | Get file → | |
| Q8_0 | 1.7 GB | 2.2 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.97 GB file, ~1.5 GB memory). For 4 GB VRAM, use Q3_K_S (0.72 GB file, ~1.3 GB memory). For 2 GB VRAM, use Q2_K (0.62 GB file, ~1.2 GB memory).
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 Q8_0 (1.7 GB file, about 2.3 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.
The Q8_0 file is 1.7 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 0.6 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
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 Q8_0: the 1.7 GB file needs about 2.3 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: Q2_K is 0.6 GB, Q3_K_S is 0.7 GB, Q3_K_M is 0.8 GB, Q3_K_L is 0.9 GB, Q4_0 is 0.9 GB, Q4_K_S is 0.9 GB and 8 more.
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 QuantFactory/Refact-1_6-base-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.
Can I run Refact 1 6 base on 8 GB VRAM?
Yes, the Q4_K_M quantization requires about 1.5 GB VRAM, which fits on an 8 GB GPU.
Does the model support image input?
No, Refact 1 6 base has no vision capability.
What license does the model use?
The model is released under the bigscience‑openrail‑m license.