gpt oss 160b kiwi i1 needs about 101.8 GB of memory at IQ3_S (a 90.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 17 quants, from 0.2 GB to 97.2 GB (Q3_K_M).
gpt oss 160b kiwi i1 is a 160B-parameter gpt-oss model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 17 quant files, from 0.2 GB to 97.2 GB (Q3_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.2 GB | 0.7 GB | Fits | Get file → | |
| IQ1_M | 90.3 GB | 101.7 GB | Too big | Get file → | |
| IQ1_S | 90.3 GB | 101.7 GB | Too big | Get file → | |
| IQ2_XXS | 90.3 GB | 101.7 GB | Too big | Get file → | |
| IQ2_XS | 90.4 GB | 101.7 GB | Too big | Get file → | |
| Q3_K_S | 90.4 GB | 101.8 GB | Too big | Get file → | |
| IQ2_M | 90.4 GB | 101.8 GB | Too big | Get file → | |
| IQ2_S | 90.4 GB | 101.8 GB | Too big | Get file → | |
| IQ3_S | 90.4 GB | 101.8 GB | Too big | Get file → | |
| IQ3_XS | 90.4 GB | 101.8 GB | Too big | Get file → | |
| IQ3_XXS | 90.4 GB | 101.8 GB | Too big | Get file → | |
| Q2_K | 90.4 GB | 101.8 GB | Too big | Get file → | |
| IQ4_XS | 90.5 GB | 101.8 GB | Too big | Get file → | |
| Q4_0 | 90.8 GB | 102.2 GB | Too big | Get file → | |
| Q2_K_S | 91.1 GB | 102.5 GB | Too big | Get file → | |
| IQ3_M | 91.2 GB | 102.7 GB | Too big | Get file → | |
| Q3_K_M | 97.2 GB | 109.4 GB | Too big | Get file → |
What GPU do you need for gpt oss 160b kiwi i1?
These figures add the file size, an fp16 KV cache at an 8K context window 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 the main file (0.2 GB file, about 0.7 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 0.7 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 0.7 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 0.7 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 0.7 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 0.7 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 0.7 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 0.7 GB in use).
Which gpt oss 160b kiwi i1 quant should you choose?
IQ3_S (90.4 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 the first one in the table at 0.2 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about gpt oss 160b kiwi i1
How much VRAM does gpt oss 160b kiwi i1 need?
About 101.8 GB at IQ3_S 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 i1 on an 8 GB GPU?
Yes, with the smaller files: the 0.2 GB file needs about 0.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of gpt oss 160b kiwi i1 GGUF?
It depends on the quant: file is 0.2 GB, IQ1_M is 90.3 GB, IQ1_S is 90.3 GB, IQ2_XXS is 90.3 GB, IQ2_XS is 90.4 GB, Q3_K_S is 90.4 GB and 11 more.
What context length does gpt oss 160b kiwi i1 support?
The GGUF header lists a trained context length of 131,072 tokens (128K).
Where can I download gpt oss 160b kiwi i1 GGUF?
The files are on Hugging Face in the mradermacher/gpt-oss-160b-kiwi-i1-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 i1 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.