Bucharest 0.2 needs about 8.6 GB of memory at Q4_K_M (a 6.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 17 quants, from 2.4 GB (IQ1_S) to 11.4 GB (Q8_0).
Bucharest 0.2 is a 10.7B-parameter Bucharest model in GGUF format, quantized by tsunemoto. Its trained context length is 6K tokens. The repository has 17 quant files, from 2.4 GB (IQ1_S) to 11.4 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 2.4 GB | 4.0 GB | Fits | Get file → | |
| IQ2_XXS | 2.9 GB | 4.6 GB | Fits | Get file → | |
| IQ2_XS | 3.2 GB | 4.9 GB | Fits | Get file → | |
| Q2_K | 4.5 GB | 6.2 GB | Fits | Get file → | |
| Q3_K_S | 4.7 GB | 6.3 GB | Fits | Get file → | |
| Q3_K_M | 5.2 GB | 6.9 GB | Fits | Get file → | |
| Q3_K_L | 5.7 GB | 7.3 GB | Tight | Get file → | |
| Q4_0 | 6.1 GB | 7.8 GB | Tight | Get file → | |
| Q4_K_S | 6.1 GB | 7.8 GB | Tight | Get file → | |
| Q4_K_M | 6.5 GB | 8.1 GB | Too big | Get file → | |
| Q4_1 | 6.7 GB | 8.4 GB | Too big | Get file → | |
| Q5_0 | 7.4 GB | 9.1 GB | Too big | Get file → | |
| Q5_K_S | 7.4 GB | 9.1 GB | Too big | Get file → | |
| Q5_K_M | 7.6 GB | 9.3 GB | Too big | Get file → | |
| Q5_1 | 8.1 GB | 9.7 GB | Too big | Get file → | |
| Q6_K | 8.8 GB | 10.5 GB | Too big | Get file → | |
| Q8_0 | 11.4 GB | 13.1 GB | Too big | Get file → |
What GPU do you need for Bucharest 0.2?
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 IQ2_XS (3.2 GB file, about 5.3 GB in use).
- 8 GB VRAM: the best quant that fits is Q3_K_L (5.7 GB file, about 7.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (8.8 GB file, about 10.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (11.4 GB file, about 13.5 GB in use).
Which Bucharest 0.2 quant should you choose?
Q4_K_M is the usual starting point for Bucharest 0.2: it balances file size and quality well. Here it is a 6.5 GB file.
The Q8_0 file is 11.4 GB, about 1.8 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 IQ1_S at 2.4 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 Bucharest 0.2
How much VRAM does Bucharest 0.2 need?
About 8.6 GB at Q4_K_M with an 8K context window. That is the 6.5 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 Bucharest 0.2 on an 8 GB GPU?
Yes, with Q3_K_L: the 5.7 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Bucharest 0.2 GGUF?
It depends on the quant: IQ1_S is 2.4 GB, IQ2_XXS is 2.9 GB, IQ2_XS is 3.2 GB, Q2_K is 4.5 GB, Q3_K_S is 4.7 GB, Q3_K_M is 5.2 GB and 11 more.
What context length does Bucharest 0.2 support?
The GGUF header lists a trained context length of 6,000 tokens (6K). The KV cache grows with the context you use: about 1.6 GB at 8K and 1.2 GB at 6K.
Where can I download Bucharest 0.2 GGUF?
The files are on Hugging Face in the tsunemoto/Bucharest-0.2-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.