Gpt Oss 160b Kiwi needs about 91.5 GB of memory at Q2_K (a 90.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 4 quants, from 90.4 GB (Q3_K_S) to 97.2 GB (Q3_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 2.4 GB.
Gpt Oss 160b Kiwi is a 160B-parameter gpt-oss model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 4 quant files, from 90.4 GB (Q3_K_S) to 97.2 GB (Q3_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 90.4 GB | 91.5 GB | Too big | Get file → | |
| Q2_K | 90.4 GB | 91.5 GB | Too big | Get file → | |
| IQ4_XS | 91.6 GB | 92.7 GB | Too big | Get file → | |
| Q3_K_M | 97.2 GB | 98.3 GB | Too big | Get file → |
What GPU do you need for Gpt Oss 160b Kiwi?
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: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which Gpt Oss 160b Kiwi quant should you choose?
Q2_K (90.4 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 Q3_K_S at 90.4 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Gpt Oss 160b Kiwi
How much VRAM does Gpt Oss 160b Kiwi need?
About 91.5 GB at Q2_K with an 8K context window. That is the 90.4 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 Gpt Oss 160b Kiwi on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 91.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Gpt Oss 160b Kiwi GGUF?
It depends on the quant: Q3_K_S is 90.4 GB, Q2_K is 90.4 GB, IQ4_XS is 91.6 GB, Q3_K_M is 97.2 GB.
What context length does Gpt Oss 160b Kiwi support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.4 GB at 32K.
Where can I download Gpt Oss 160b Kiwi GGUF?
The files are on Hugging Face in the mradermacher/gpt-oss-160b-kiwi-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 Gpt Oss 160b Kiwi 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.