Fable Traces needs about 5.0 GB of memory at Q6_K (a 3.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
Fable Traces is a 4.02B-parameter Fable model in GGUF format, quantized by gopi87. Its trained context length is 256K tokens. The repository has 1 quant file, from 3.3 GB (Q6_K) to 3.3 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K | 3.3 GB | 5.0 GB | Fits | Get file → |
What GPU do you need for Fable Traces?
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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q6_K (3.3 GB file, about 5.0 GB in use).
Which Fable Traces quant should you choose?
Q6_K (3.3 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Fable Traces
How much VRAM does Fable Traces need?
About 5.0 GB at Q6_K with an 8K context window. That is the 3.3 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 Fable Traces on an 8 GB GPU?
Yes, with Q6_K: the 3.3 GB file needs about 5.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Fable Traces GGUF?
It depends on the quant: Q6_K is 3.3 GB.
What context length does Fable Traces support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.
Where can I download Fable Traces GGUF?
The files are on Hugging Face in the gopi87/fable-traces-Q6_K-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 Fable Traces use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.