qwen2.5 bakeneko 32b instruct needs about 22.5 GB of memory at Q4_K (a 19.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 8 quants, from 12.3 GB (Q2_K) to 34.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
qwen2.5 bakeneko 32b instruct is a 32.8B-parameter Qwen model in GGUF format, quantized by rinna. Its trained context length is 32K tokens. The repository has 8 quant files, from 12.3 GB (Q2_K) to 34.8 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 12.3 GB | 15.0 GB | Too big | Get file → | |
| Q3_K | 15.9 GB | 18.6 GB | Too big | Get file → | |
| Q4_0 | 18.6 GB | 21.3 GB | Too big | Get file → | |
| Q4_K | 19.9 GB | 22.5 GB | Too big | Get file → | |
| Q5_0 | 22.6 GB | 25.3 GB | Too big | Get file → | |
| Q5_K | 23.3 GB | 25.9 GB | Too big | Get file → | |
| Q6_K | 26.9 GB | 29.5 GB | Too big | Get file → | |
| Q8_0 | 34.8 GB | 37.5 GB | Too big | Get file → |
What GPU do you need for qwen2.5 bakeneko 32b instruct?
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: the best quant that fits is Q2_K (12.3 GB file, about 15.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K (19.9 GB file, about 22.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (26.9 GB file, about 29.5 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (34.8 GB file, about 37.5 GB in use).
Which qwen2.5 bakeneko 32b instruct quant should you choose?
Q4_K (19.9 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is Q2_K at 12.3 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 qwen2.5 bakeneko 32b instruct
How much VRAM does qwen2.5 bakeneko 32b instruct need?
About 22.5 GB at Q4_K with an 8K context window. That is the 19.9 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 qwen2.5 bakeneko 32b instruct on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 15.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of qwen2.5 bakeneko 32b instruct GGUF?
It depends on the quant: Q2_K is 12.3 GB, Q3_K is 15.9 GB, Q4_0 is 18.6 GB, Q4_K is 19.9 GB, Q5_0 is 22.6 GB, Q5_K is 23.3 GB and 2 more.
What context length does qwen2.5 bakeneko 32b instruct support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download qwen2.5 bakeneko 32b instruct GGUF?
The files are on Hugging Face in the rinna/qwen2.5-bakeneko-32b-instruct-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 qwen2.5 bakeneko 32b instruct 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.