QW

MANGO Qwen3 Omni 30B A3B Instruct

QwenGGUF by mradermacherUpdated 2026-07-03
Download on Hugging Face
Parameters30.5B
Context64K
Layers48
Architectureqwen3vlmoe
Smallest quant0.1 GB
Quick answer

MANGO Qwen3 Omni 30B A3B Instruct needs about 19.9 GB of memory at Q4_K_M (a 18.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.1 GB to 25.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

MANGO Qwen3 Omni 30B A3B Instruct – Thai‑English vision‑text LLM

MANGO Qwen3 Omni 30B A3B Instruct is a 30.5B parameter mixture‑of‑experts model fine‑tuned with LoRA on a mixed vision‑text and text‑only corpus. It supports Thai and English text input and image input, producing text output. The model is based on Qwen3‑Omni‑30B‑A3B‑Instruct.

Good at

  • Thai language reasoning
  • Vision‑text joint tasks
  • Instruction following

Limits

  • No audio/video fine‑tuning
  • Requires 8‑k context for memory estimates
  • License inherited from base model

Best for

  • Thai chatbots
  • Vision‑text QA
  • Multilingual summarization

Who it’s for. Developers building Thai‑English chat or vision‑language applications. Researchers testing multimodal fine‑tuning on low‑resource languages.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 1.4 GB
Fits Get file →
IQ1_S6.4 GB 7.7 GB
Tight Get file →
IQ1_M7.1 GB 8.4 GB
Too big Get file →
IQ2_XXS8.2 GB 9.5 GB
Too big Get file →
IQ2_XS9.1 GB 10.4 GB
Too big Get file →
IQ2_S9.3 GB 10.6 GB
Too big Get file →
IQ2_M10.2 GB 11.5 GB
Too big Get file →
Q2_K_S10.5 GB 11.8 GB
Too big Get file →
Q2_K11.3 GB 12.6 GB
Too big Get file →
IQ3_XXS11.8 GB 13.2 GB
Too big Get file →
IQ3_XS12.6 GB 13.9 GB
Too big Get file →
Q3_K_S13.3 GB 14.6 GB
Too big Get file →
IQ3_S13.3 GB 14.6 GB
Too big Get file →
IQ3_M13.5 GB 14.8 GB
Too big Get file →
Q3_K_M14.7 GB 16.0 GB
Too big Get file →
Q3_K_L15.9 GB 17.2 GB
Too big Get file →
IQ4_XS16.4 GB 17.7 GB
Too big Get file →
Q4_017.4 GB 18.7 GB
Too big Get file →
Q4_K_S17.5 GB 18.8 GB
Too big Get file →
Q4_K_M18.6 GB 19.9 GB
Too big Get file →
Q4_119.2 GB 20.5 GB
Too big Get file →
Q5_K_S21.1 GB 22.4 GB
Too big Get file →
Q5_K_M21.7 GB 23.0 GB
Too big Get file →
Q6_K25.1 GB 26.4 GB
Too big Get file →

For 8‑GB VRAM use IQ1_S (6.42 GB, 7.7 GB memory). For 12‑GB VRAM use Q2_M (10.17 GB, 11.5 GB memory). For 24‑GB VRAM use Q6_K (25.09 GB, 26.4 GB memory). Estimates are approximate.

What GPU do you need for MANGO Qwen3 Omni 30B A3B 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: the best quant that fits is the main file (0.1 GB file, about 1.4 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.4 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ1_S (6.4 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q2_K_S (10.5 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q3_K_M (14.7 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (21.7 GB file, about 23.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (25.1 GB file, about 26.4 GB in use).

Which MANGO Qwen3 Omni 30B A3B Instruct quant should you choose?

Q4_K_M is the usual starting point for MANGO Qwen3 Omni 30B A3B Instruct: it balances file size and quality well. Here it is a 18.6 GB file.

If memory is tight, the smallest file is the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3vlmoe
Parameters30.5B (approximate, mixture of experts)
Active parameters3B
Layers48
Trained context65,536 tokens
KV cache (fp16)96 KB per token

Source

Quantized bymradermacher
FamilyQwen
Licenseother
Downloads (HF)1,512
Last updated2026-07-03

Frequently asked questions about MANGO Qwen3 Omni 30B A3B Instruct

How much VRAM does MANGO Qwen3 Omni 30B A3B Instruct need?

About 19.9 GB at Q4_K_M with an 8K context window. That is the 18.6 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 MANGO Qwen3 Omni 30B A3B Instruct on an 8 GB GPU?

Yes, with IQ1_S: the 6.4 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MANGO Qwen3 Omni 30B A3B Instruct GGUF?

It depends on the quant: file is 0.1 GB, IQ1_S is 6.4 GB, IQ1_M is 7.1 GB, IQ2_XXS is 8.2 GB, IQ2_XS is 9.1 GB, IQ2_S is 9.3 GB and 18 more.

What context length does MANGO Qwen3 Omni 30B A3B Instruct support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download MANGO Qwen3 Omni 30B A3B Instruct GGUF?

The files are on Hugging Face in the mradermacher/MANGO-Qwen3-Omni-30B-A3B-Instruct-i1-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 MANGO Qwen3 Omni 30B A3B Instruct use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

Yes, the IQ1_S quant is 6.42 GB and requires about 7.7 GB VRAM at 8k context.

Does the model support vision input?

Yes, it accepts image input and outputs text, but the vision encoder is frozen from fine‑tuning.

What languages can it understand?

Thai and English are supported; other languages are not fine‑tuned.

Other GGUFs of MANGO-Qwen3-Omni-30B-A3B-Instruct

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other medium models

All medium models →