KiwiMate Large 1.0 needs about 72.3 GB of memory at F16 (a 71.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.
KiwiMate Large 1.0 is a 35.5B-parameter Qwen model in GGUF format, quantized by KiwiMate. Its trained context length is 256K tokens. The repository has 1 quant file, from 71.1 GB (F16) to 71.1 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 71.1 GB (2 parts) | 72.3 GB | Too big | Get file → |
What GPU do you need for KiwiMate Large 1.0?
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 KiwiMate Large 1.0 quant should you choose?
F16 (71.1 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about KiwiMate Large 1.0
How much VRAM does KiwiMate Large 1.0 need?
About 72.3 GB at F16 with an 8K context window. That is the 71.1 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 KiwiMate Large 1.0 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 72.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of KiwiMate Large 1.0 GGUF?
It depends on the quant: F16 is 71.1 GB.
What context length does KiwiMate Large 1.0 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.8 GB at 32K.
Where can I download KiwiMate Large 1.0 GGUF?
The files are on Hugging Face in the KiwiMate/KiwiMate-Large-1.0 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does KiwiMate Large 1.0 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.