K2 V2 base final needs about 54.7 GB of memory at Q5_K_M (a 51.5 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 10.7 GB.
K2 V2 base final is a 72.6B-parameter Base model in GGUF format, quantized by mesh-ops. Its trained context length is 32K tokens. The repository has 1 quant file, from 51.5 GB (Q5_K_M) to 51.5 GB (Q5_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K_M | 51.5 GB | 54.7 GB | Too big | Get file → |
What GPU do you need for K2 V2 base final?
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 K2 V2 base final quant should you choose?
Q5_K_M (51.5 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 K2 V2 base final
How much VRAM does K2 V2 base final need?
About 54.7 GB at Q5_K_M with an 8K context window. That is the 51.5 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 K2 V2 base final on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 54.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of K2 V2 base final GGUF?
It depends on the quant: Q5_K_M is 51.5 GB.
What context length does K2 V2 base final support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.
Where can I download K2 V2 base final GGUF?
The files are on Hugging Face in the mesh-ops/K2-V2-base_final-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 K2 V2 base final 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.