petals team StableBeluga2 needs about 29.0 GB of memory at Q2_K (a 25.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 10 quants, from 6.9 GB (IQ4_XS) to 38.9 GB (Q4_0).
petals team StableBeluga2 is a 68B-parameter Petals model in GGUF format, quantized by RichardErkhov. The repository has 10 quant files, from 6.9 GB (IQ4_XS) to 38.9 GB (Q4_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_XS | 6.9 GB | 8.2 GB | Too big | Get file → | |
| IQ3_XS | 17.3 GB | 19.9 GB | Too big | Get file → | |
| IQ3_M | 18.1 GB | 20.8 GB | Too big | Get file → | |
| Q3_K | 23.9 GB | 27.3 GB | Too big | Get file → | |
| Q2_K | 25.5 GB | 29.0 GB | Too big | Get file → | |
| IQ3_S | 29.9 GB | 34.0 GB | Too big | Get file → | |
| Q3_K_S | 29.9 GB | 34.0 GB | Too big | Get file → | |
| Q3_K_L | 31.4 GB | 35.7 GB | Too big | Get file → | |
| Q3_K_M | 33.3 GB | 37.8 GB | Too big | Get file → | |
| Q4_0 | 38.9 GB | 44.0 GB | Too big | Get file → |
What GPU do you need for petals team StableBeluga2?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is IQ4_XS (6.9 GB file, about 8.2 GB in use).
- 16 GB VRAM: the best quant that fits is IQ4_XS (6.9 GB file, about 8.2 GB in use).
- 24 GB VRAM: the best quant that fits is IQ3_M (18.1 GB file, about 20.8 GB in use).
- 32 GB VRAM: the best quant that fits is Q2_K (25.5 GB file, about 29.0 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_0 (38.9 GB file, about 44.0 GB in use).
Which petals team StableBeluga2 quant should you choose?
Q2_K (25.5 GB) is the middle option in this repository. 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.
If memory is tight, the smallest file is IQ4_XS at 6.9 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about petals team StableBeluga2
How much VRAM does petals team StableBeluga2 need?
About 29.0 GB at Q2_K with an 8K context window. That is the 25.5 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 petals team StableBeluga2 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of petals team StableBeluga2 GGUF?
It depends on the quant: IQ4_XS is 6.9 GB, IQ3_XS is 17.3 GB, IQ3_M is 18.1 GB, Q3_K is 23.9 GB, Q2_K is 25.5 GB, IQ3_S is 29.9 GB and 4 more.
Where can I download petals team StableBeluga2 GGUF?
The files are on Hugging Face in the RichardErkhov/petals-team_-_StableBeluga2-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.