OpenBuddy openbuddy zero 56b v21.2 32k needs about 28.5 GB of memory at IQ3_S (a 24.7 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 8 quants, from 21.0 GB (Q2_K) to 29.9 GB (Q3_K_L). Longer context needs more: at 32K tokens the KV cache alone adds about 13.4 GB.
OpenBuddy openbuddy zero 56b v21.2 32k is a 56.7B-parameter Openbuddy model in GGUF format, quantized by RichardErkhov. Its trained context length is 128K tokens. The repository has 8 quant files, from 21.0 GB (Q2_K) to 29.9 GB (Q3_K_L).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 21.0 GB | 24.9 GB | Too big | Get file → | |
| IQ3_XS | 23.3 GB | 27.2 GB | Too big | Get file → | |
| Q3_K_S | 24.6 GB | 28.4 GB | Too big | Get file → | |
| IQ3_S | 24.7 GB | 28.5 GB | Too big | Get file → | |
| IQ3_M | 25.6 GB | 29.4 GB | Too big | Get file → | |
| Q3_K | 27.4 GB | 31.2 GB | Too big | Get file → | |
| Q3_K_M | 27.4 GB | 31.2 GB | Too big | Get file → | |
| Q3_K_L | 29.9 GB | 33.7 GB | Too big | Get file → |
What GPU do you need for OpenBuddy openbuddy zero 56b v21.2 32k?
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: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is Q3_K (27.4 GB file, about 31.2 GB in use).
- 48 GB VRAM: the best quant that fits is Q3_K_L (29.9 GB file, about 33.7 GB in use).
Which OpenBuddy openbuddy zero 56b v21.2 32k quant should you choose?
IQ3_S (24.7 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is Q2_K at 21.0 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
Frequently asked questions about OpenBuddy openbuddy zero 56b v21.2 32k
How much VRAM does OpenBuddy openbuddy zero 56b v21.2 32k need?
About 28.5 GB at IQ3_S with an 8K context window. That is the 24.7 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 OpenBuddy openbuddy zero 56b v21.2 32k on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 24.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of OpenBuddy openbuddy zero 56b v21.2 32k GGUF?
It depends on the quant: Q2_K is 21.0 GB, IQ3_XS is 23.3 GB, Q3_K_S is 24.6 GB, IQ3_S is 24.7 GB, IQ3_M is 25.6 GB, Q3_K is 27.4 GB and 2 more.
What context length does OpenBuddy openbuddy zero 56b v21.2 32k support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.4 GB at 8K and 13.4 GB at 32K.
Where can I download OpenBuddy openbuddy zero 56b v21.2 32k GGUF?
The files are on Hugging Face in the RichardErkhov/OpenBuddy_-_openbuddy-zero-56b-v21.2-32k-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 OpenBuddy openbuddy zero 56b v21.2 32k use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.