hikari 4x7B needs about 50.1 GB of memory at F16 (a 48.6 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 4.3 GB.
hikari 4x7B is a 24.3B-parameter Hikari model in GGUF format, quantized by saucam. Its trained context length is 32K tokens. The repository has 1 quant file, from 48.6 GB (F16) to 48.6 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 48.6 GB | 50.1 GB | Too big | Get file → |
What GPU do you need for hikari 4x7B?
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 hikari 4x7B quant should you choose?
F16 (48.6 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 hikari 4x7B
How much VRAM does hikari 4x7B need?
About 50.1 GB at F16 with an 8K context window. That is the 48.6 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 hikari 4x7B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 50.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of hikari 4x7B GGUF?
It depends on the quant: F16 is 48.6 GB.
What context length does hikari 4x7B support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download hikari 4x7B GGUF?
The files are on Hugging Face in the saucam/hikari-4x7B-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.