KA

Karakuri Vl 32b Instruct 2507

KarakuriGGUF by mmngaUpdated 2025-07-09
Download on Hugging Face
Parameters32.8B
Context125K
Layers64
Architectureqwen2vl
Smallest quant14.8 GB
Quick answer

Karakuri Vl 32b Instruct 2507 needs about 22.5 GB of memory at Q4_K_M (a 19.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 13 quants, from 14.8 GB (IQ3_M) to 34.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Karakuri Vl 32b Instruct 2507 is a 32.8B-parameter Karakuri model in GGUF format, quantized by mmnga. Its trained context length is 125K tokens. The repository has 13 quant files, from 14.8 GB (IQ3_M) to 34.8 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_M14.8 GB 17.5 GB
Too big Get file →
Q3_K_M15.9 GB 18.6 GB
Too big Get file →
Q3_K_L17.2 GB 19.9 GB
Too big Get file →
IQ4_XS17.7 GB 20.3 GB
Too big Get file →
Q4_018.6 GB 21.3 GB
Too big Get file →
IQ4_NL18.7 GB 21.3 GB
Too big Get file →
Q4_K_S18.8 GB 21.4 GB
Too big Get file →
Q4_K_M19.9 GB 22.5 GB
Too big Get file →
Q5_022.6 GB 25.3 GB
Too big Get file →
Q5_K_S22.6 GB 25.3 GB
Too big Get file →
Q5_K_M23.3 GB 25.9 GB
Too big Get file →
Q6_K26.9 GB 29.5 GB
Too big Get file →
Q8_034.8 GB 37.5 GB
Too big Get file →

What GPU do you need for Karakuri Vl 32b Instruct 2507?

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: the best quant that fits is Q4_K_M (19.9 GB file, about 22.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (26.9 GB file, about 29.5 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (34.8 GB file, about 37.5 GB in use).

Which Karakuri Vl 32b Instruct 2507 quant should you choose?

Q4_K_M is the usual starting point for Karakuri Vl 32b Instruct 2507: it balances file size and quality well. Here it is a 19.9 GB file.

The Q8_0 file is 34.8 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 IQ3_M at 14.8 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2vl
Parameters32.8B
Layers64
Trained context128,000 tokens
KV cache (fp16)256 KB per token

Source

Quantized bymmnga
FamilyKarakuri
Licenseapache-2.0
Downloads (HF)213
Last updated2025-07-09

Frequently asked questions about Karakuri Vl 32b Instruct 2507

How much VRAM does Karakuri Vl 32b Instruct 2507 need?

About 22.5 GB at Q4_K_M with an 8K context window. That is the 19.9 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 Karakuri Vl 32b Instruct 2507 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Karakuri Vl 32b Instruct 2507 GGUF?

It depends on the quant: IQ3_M is 14.8 GB, Q3_K_M is 15.9 GB, Q3_K_L is 17.2 GB, IQ4_XS is 17.7 GB, Q4_0 is 18.6 GB, IQ4_NL is 18.7 GB and 7 more.

What context length does Karakuri Vl 32b Instruct 2507 support?

The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Karakuri Vl 32b Instruct 2507 GGUF?

The files are on Hugging Face in the mmnga/karakuri-vl-32b-instruct-2507-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 Karakuri Vl 32b Instruct 2507 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.

Other GGUFs of karakuri-vl-32b-instruct-2507

Similar models

Browse all →

More from mmnga

All by mmnga →

More Karakuri models

All Karakuri →

Other medium models

All medium models →