LL

Llm Jp 4 Kappa 32b A3B v0.1

LlmGGUF by mmnga-oUpdated 2026-05-26
Download on Hugging Face
Parameters32.1B
Context64K
Layers32
Architectureqwen3moe
Smallest quant15.6 GB
Quick answer

Llm Jp 4 Kappa 32b A3B v0.1 needs about 22.4 GB of memory at Q4_K_M (a 21.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 14 quants, from 15.6 GB (IQ3_M) to 34.2 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.

Llm Jp 4 Kappa 32b A3B v0.1 is a 32.1B-parameter Llm model in GGUF format, quantized by mmnga-o. Its trained context length is 64K tokens. The repository has 14 quant files, from 15.6 GB (IQ3_M) to 34.2 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_M15.6 GB 16.6 GB
Too big Get file →
Q3_K_M16.7 GB 17.8 GB
Too big Get file →
Q3_K_L17.4 GB 18.4 GB
Too big Get file →
IQ4_XS17.6 GB 18.6 GB
Too big Get file →
MXFP4_MOE18.1 GB 19.2 GB
Too big Get file →
Q4_018.2 GB 19.3 GB
Too big Get file →
IQ4_NL18.3 GB 19.3 GB
Too big Get file →
Q4_K_S19.6 GB 20.6 GB
Too big Get file →
Q4_K_M21.4 GB 22.4 GB
Too big Get file →
Q5_022.2 GB 23.2 GB
Too big Get file →
Q5_K_S22.8 GB 23.9 GB
Too big Get file →
Q5_K_M24.4 GB 25.4 GB
Too big Get file →
Q6_K28.8 GB 29.9 GB
Too big Get file →
Q8_034.2 GB 35.2 GB
Too big Get file →

What GPU do you need for Llm Jp 4 Kappa 32b A3B v0.1?

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 Q5_K_S (22.8 GB file, about 23.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (28.8 GB file, about 29.9 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (34.2 GB file, about 35.2 GB in use).

Which Llm Jp 4 Kappa 32b A3B v0.1 quant should you choose?

Q4_K_M is the usual starting point for Llm Jp 4 Kappa 32b A3B v0.1: it balances file size and quality well. Here it is a 21.4 GB file.

The Q8_0 file is 34.2 GB, about 1.6 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 15.6 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

Architectureqwen3moe
Parameters32.1B (approximate, mixture of experts)
Active parameters3B
Layers32
Trained context65,536 tokens
KV cache (fp16)64 KB per token

Source

Quantized bymmnga-o
FamilyLlm
Licenseapache-2.0
Downloads (HF)377
Last updated2026-05-26

Frequently asked questions about Llm Jp 4 Kappa 32b A3B v0.1

How much VRAM does Llm Jp 4 Kappa 32b A3B v0.1 need?

About 22.4 GB at Q4_K_M with an 8K context window. That is the 21.4 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 Llm Jp 4 Kappa 32b A3B v0.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Llm Jp 4 Kappa 32b A3B v0.1 GGUF?

It depends on the quant: IQ3_M is 15.6 GB, Q3_K_M is 16.7 GB, Q3_K_L is 17.4 GB, IQ4_XS is 17.6 GB, MXFP4_MOE is 18.1 GB, Q4_0 is 18.2 GB and 8 more.

What context length does Llm Jp 4 Kappa 32b A3B v0.1 support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.1 GB at 32K.

Where can I download Llm Jp 4 Kappa 32b A3B v0.1 GGUF?

The files are on Hugging Face in the mmnga-o/llm-jp-4-kappa-32b-a3b-v0.1-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 Llm Jp 4 Kappa 32b A3B v0.1 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 mmnga-o

All by mmnga-o →

More Llm models

All Llm →

Other medium models

All medium models →