QW

RWKV Qwen3 30B A3B Instruct Hxa07D L8

QwenGGUF by OpenMOSEUpdated 2025-12-29
Download on Hugging Face
Parameters30.8B
Context256K
Layers48
Architecturerwkv07d_moe
Smallest quant12.4 GB
Quick answer

RWKV Qwen3 30B A3B Instruct Hxa07D L8 needs about 13.7 GB of memory at IQ3_XXS (a 12.4 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 2 quants, from 12.4 GB (IQ3_XXS) to 16.9 GB (IQ4_XS). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

RWKV Qwen3 30B A3B Instruct Hxa07D L8 is a 30.8B-parameter Qwen model in GGUF format, quantized by OpenMOSE. Its trained context length is 256K tokens. The repository has 2 quant files, from 12.4 GB (IQ3_XXS) to 16.9 GB (IQ4_XS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_XXS12.4 GB 13.7 GB
Too big Get file →
IQ4_XS16.9 GB 18.2 GB
Too big Get file →

What GPU do you need for RWKV Qwen3 30B A3B Instruct Hxa07D L8?

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: the best quant that fits is IQ3_XXS (12.4 GB file, about 13.7 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ4_XS (16.9 GB file, about 18.2 GB in use).

Which RWKV Qwen3 30B A3B Instruct Hxa07D L8 quant should you choose?

IQ3_XXS (12.4 GB) is the middle option in this repository. 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

Architecturerwkv07d_moe
Parameters30.8B (approximate, mixture of experts)
Active parameters3B
Layers48
Trained context262,144 tokens
KV cache (fp16)96 KB per token

Source

Quantized byOpenMOSE
FamilyQwen
Licenseapache-2.0
Downloads (HF)50
Last updated2025-12-29

Frequently asked questions about RWKV Qwen3 30B A3B Instruct Hxa07D L8

How much VRAM does RWKV Qwen3 30B A3B Instruct Hxa07D L8 need?

About 13.7 GB at IQ3_XXS with an 8K context window. That is the 12.4 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 RWKV Qwen3 30B A3B Instruct Hxa07D L8 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of RWKV Qwen3 30B A3B Instruct Hxa07D L8 GGUF?

It depends on the quant: IQ3_XXS is 12.4 GB, IQ4_XS is 16.9 GB.

What context length does RWKV Qwen3 30B A3B Instruct Hxa07D L8 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download RWKV Qwen3 30B A3B Instruct Hxa07D L8 GGUF?

The files are on Hugging Face in the OpenMOSE/RWKV-Qwen3-30B-A3B-Instruct-hxa07d-L8-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 RWKV Qwen3 30B A3B Instruct Hxa07D L8 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 OpenMOSE

All by OpenMOSE →

More Qwen models

All Qwen →

Other medium models

All medium models →