llama kit needs about 27.6 GB of memory at Q5_K_M (a 26.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
llama kit is a 34.7B-parameter Llama model in GGUF format, quantized by SKPW2. Its trained context length is 320K tokens. The repository has 1 quant file, from 26.5 GB (Q5_K_M) to 26.5 GB (Q5_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K_M | 26.5 GB | 27.6 GB | Too big | Get file → |
What GPU do you need for llama kit?
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: the best quant that fits is Q5_K_M (26.5 GB file, about 27.6 GB in use).
Which llama kit quant should you choose?
Q5_K_M (26.5 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about llama kit
How much VRAM does llama kit need?
About 27.6 GB at Q5_K_M with an 8K context window. That is the 26.5 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 llama kit on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 27.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of llama kit GGUF?
It depends on the quant: Q5_K_M is 26.5 GB.
What context length does llama kit support?
The GGUF header lists a trained context length of 327,680 tokens (320K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.
Where can I download llama kit GGUF?
The files are on Hugging Face in the SKPW2/llama-kit repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does llama kit 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.