buzz-small needs about 3.7 GB of memory at Q4_K_M (a 2.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 19 quants, from 0.2 GB (IQ1_S) to 17.3 GB (F32).
buzz-small is a 3B-parameter Buzz model in GGUF format, quantized by H-D-T. Its trained context length is 8K tokens. The repository has 19 quant files, from 0.2 GB (IQ1_S) to 17.3 GB (F32).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 0.2 GB | 1.2 GB | Fits | Get file → | |
| Q2_K | 0.9 GB | 1.9 GB | Fits | Get file → | |
| Q2_K_S | 1.7 GB | 2.7 GB | Fits | Get file → | |
| Q3_K_S | 2.1 GB | 3.1 GB | Fits | Get file → | |
| Q3_K | 2.2 GB | 3.2 GB | Fits | Get file → | |
| Q3_K_M | 2.2 GB | 3.2 GB | Fits | Get file → | |
| Q3_K_L | 2.4 GB | 3.4 GB | Fits | Get file → | |
| Q4_0 | 2.6 GB | 3.6 GB | Fits | Get file → | |
| Q4_K_S | 2.6 GB | 3.6 GB | Fits | Get file → | |
| Q4_K | 2.7 GB | 3.7 GB | Fits | Get file → | |
| Q4_K_M | 2.7 GB | 3.7 GB | Fits | Get file → | |
| Q4_1 | 2.8 GB | 3.8 GB | Fits | Get file → | |
| Q5_K_S | 3.1 GB | 4.1 GB | Fits | Get file → | |
| Q5_0 | 3.1 GB | 4.1 GB | Fits | Get file → | |
| Q5_K | 3.1 GB | 4.1 GB | Fits | Get file → | |
| Q5_K_M | 3.1 GB | 4.1 GB | Fits | Get file → | |
| Q5_1 | 3.3 GB | 4.3 GB | Fits | Get file → | |
| Q6_K | 3.6 GB | 4.6 GB | Fits | Get file → | |
| F32 | 17.3 GB | 18.3 GB | Too big | Get file → |
What GPU do you need for buzz-small?
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_1 (2.8 GB file, about 3.8 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (3.6 GB file, about 4.6 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (3.6 GB file, about 4.6 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (3.6 GB file, about 4.6 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (3.6 GB file, about 4.6 GB in use).
- 24 GB VRAM: the best quant that fits is F32 (17.3 GB file, about 18.3 GB in use).
Which buzz-small quant should you choose?
Q4_K_M is the usual starting point for buzz-small: it balances file size and quality well. Here it is a 2.7 GB file.
If memory is tight, the smallest file is IQ1_S at 0.2 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 buzz-small
How much VRAM does buzz-small need?
About 3.7 GB at Q4_K_M with an 8K context window. That is the 2.7 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 buzz-small on an 8 GB GPU?
Yes, with Q6_K: the 3.6 GB file needs about 4.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of buzz-small GGUF?
It depends on the quant: IQ1_S is 0.2 GB, Q2_K is 0.9 GB, Q2_K_S is 1.7 GB, Q3_K_S is 2.1 GB, Q3_K is 2.2 GB, Q3_K_M is 2.2 GB and 13 more.
What context length does buzz-small support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.5 GB at 8K and 0.5 GB at 8K.
Where can I download buzz-small GGUF?
The files are on Hugging Face in the H-D-T/Buzz-small-3b-v0.6.3-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.