QW

ByteShape Qwen3 Coder 30B A3B Instruct

QwenGGUF by tiktemuUpdated 2026-05-25
Download on Hugging Face
Parameters30.5B
Context256K
Layers—
Architectureqwen3moe
Smallest quant10.1 GB
Quick answer

ByteShape Qwen3 Coder 30B A3B Instruct needs about 12.6 GB of memory at IQ3_S (a 10.8 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 13 quants, from 10.1 GB (Q3_K_S) to 16.0 GB (IQ4_XS).

ByteShape Qwen3 Coder 30B A3B Instruct is a 30.5B-parameter Qwen model in GGUF format, quantized by tiktemu. Its trained context length is 256K tokens. The repository has 13 quant files, from 10.1 GB (Q3_K_S) to 16.0 GB (IQ4_XS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S10.1 GB 11.8 GB
Too big Get file →
IQ3_S10.1 GB 11.9 GB
Too big Get file →
Q3_K_S10.2 GB 11.9 GB
Too big Get file →
IQ3_S10.2 GB 12.0 GB
Too big Get file →
Q3_K_M10.3 GB 12.0 GB
Too big Get file →
Q3_K_S10.3 GB 12.0 GB
Too big Get file →
IQ3_S10.8 GB 12.6 GB
Too big Get file →
Q3_K_S11.1 GB 12.9 GB
Too big Get file →
Q3_K_S11.5 GB 13.3 GB
Too big Get file →
IQ3_S11.9 GB 13.9 GB
Too big Get file →
Q3_K_M12.7 GB 14.7 GB
Too big Get file →
IQ3_S13.3 GB 15.4 GB
Too big Get file →
IQ4_XS16.0 GB 18.4 GB
Too big Get file →

What GPU do you need for ByteShape Qwen3 Coder 30B A3B Instruct?

These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is Q3_K_S (10.3 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_S (13.3 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ4_XS (16.0 GB file, about 18.4 GB in use).

Which ByteShape Qwen3 Coder 30B A3B Instruct quant should you choose?

IQ3_S (10.8 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.

If memory is tight, the smallest file is Q3_K_S at 10.1 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
Parameters30.5B
Trained context262,144 tokens

Source

Quantized bytiktemu
FamilyQwen
Licenseapache-2.0
Downloads (HF)0
Last updated2026-05-25

Frequently asked questions about ByteShape Qwen3 Coder 30B A3B Instruct

How much VRAM does ByteShape Qwen3 Coder 30B A3B Instruct need?

About 12.6 GB at IQ3_S with an 8K context window. That is the 10.8 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 ByteShape Qwen3 Coder 30B A3B Instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of ByteShape Qwen3 Coder 30B A3B Instruct GGUF?

It depends on the quant: Q3_K_S is 10.1 GB, IQ3_S is 10.1 GB, Q3_K_S is 10.2 GB, IQ3_S is 10.2 GB, Q3_K_M is 10.3 GB, Q3_K_S is 10.3 GB and 7 more.

What context length does ByteShape Qwen3 Coder 30B A3B Instruct support?

The GGUF header lists a trained context length of 262,144 tokens (256K).

Where can I download ByteShape Qwen3 Coder 30B A3B Instruct GGUF?

The files are on Hugging Face in the tiktemu/ByteShape___Qwen3-Coder-30B-A3B-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 ByteShape Qwen3 Coder 30B A3B 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.

Other GGUFs of Qwen3-Coder-30B-A3B-Instruct

Similar models

Browse all →

More from tiktemu

All by tiktemu →

More Qwen models

All Qwen →

Other medium models

All medium models →