IN

K2 V2 Instruct

InstructGGUF by cturanUpdated 2025-12-08
Download on Hugging Face
Parameters72.6B
Context512K
Layers80
Architecturellama
Smallest quant27.5 GB
Quick answer

K2 V2 Instruct needs about 47.1 GB of memory at Q4_K_M (a 43.9 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 6 quants, from 27.5 GB (Q2_K) to 77.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

K2 V2 Instruct is a 72.6B-parameter Instruct model in GGUF format, quantized by cturan. Its trained context length is 512K tokens. The repository has 6 quant files, from 27.5 GB (Q2_K) to 77.1 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K27.5 GB 30.7 GB
Too big Get file →
Q3_K35.5 GB 38.7 GB
Too big Get file →
Q4_K_M43.9 GB 47.1 GB
Too big Get file →
Q5_K51.5 GB 54.6 GB
Too big Get file →
Q6_K59.5 GB 62.7 GB
Too big Get file →
Q8_077.1 GB 80.3 GB
Too big Get file →

What GPU do you need for K2 V2 Instruct?

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 Q2_K (27.5 GB file, about 30.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (43.9 GB file, about 47.1 GB in use).

Which K2 V2 Instruct quant should you choose?

Q4_K_M is the usual starting point for K2 V2 Instruct: it balances file size and quality well. Here it is a 43.9 GB file.

The Q8_0 file is 77.1 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 27.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters72.6B
Layers80
Trained context524,288 tokens
KV cache (fp16)320 KB per token

Source

Quantized bycturan
FamilyInstruct
Licenseapache-2.0
Downloads (HF)116
Last updated2025-12-08

Frequently asked questions about K2 V2 Instruct

How much VRAM does K2 V2 Instruct need?

About 47.1 GB at Q4_K_M with an 8K context window. That is the 43.9 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 Instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 30.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of K2 V2 Instruct GGUF?

It depends on the quant: Q2_K is 27.5 GB, Q3_K is 35.5 GB, Q4_K_M is 43.9 GB, Q5_K is 51.5 GB, Q6_K is 59.5 GB, Q8_0 is 77.1 GB.

What context length does K2 V2 Instruct support?

The GGUF header lists a trained context length of 524,288 tokens (512K). 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 Instruct GGUF?

The files are on Hugging Face in the cturan/K2-V2-Instruct-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 Instruct 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.

Similar models

Browse all →

More from cturan

All by cturan →

More Instruct models

All Instruct →

Other large models

All large models →