AE

AesCode 32B

AescodeGGUF by mradermacherUpdated 2026-10-15
Download on Hugging Face
Parameters32.8B
Context256K
Layers64
Architectureqwen3vl
Smallest quant0.0 GB
Quick answer

AesCode 32B needs about 22.4 GB of memory at Q4_K_M (a 19.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.0 GB to 26.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

AesCode 32B – 32 billion‑parameter vision‑code model for structured HTML/CSS

AesCode 32B is a 32 billion‑parameter model based on Qwen3‑VL‑32B‑Instruct. It generates information‑rich visual artifacts such as slides, posters, dashboards, and reports in editable HTML/CSS. The model is trained with cold‑start SFT and GDPO reward learning.

Good at

  • Structured HTML/CSS generation
  • Multimodal code generation
  • Verifiable visual design

Limits

  • Requires a vision‑language backbone
  • Large VRAM needed for full precision
  • No native vision‑language support in some runtimes

Best for

  • Creating editable slide decks
  • Generating dashboards from prompts
  • Research on multimodal code generation

Who it’s for. Developers and designers who need programmatic, editable visual content. Researchers studying multimodal code generation and verifiable design may also benefit.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.7 GB
Fits Get file →
IQ1_S7.3 GB 10.0 GB
Too big Get file →
IQ1_M8.0 GB 10.6 GB
Too big Get file →
IQ2_XXS9.0 GB 11.7 GB
Too big Get file →
IQ2_XS10.0 GB 12.6 GB
Too big Get file →
IQ2_S10.5 GB 13.2 GB
Too big Get file →
IQ2_M11.4 GB 14.0 GB
Too big Get file →
Q2_K_S11.5 GB 14.1 GB
Too big Get file →
Q2_K12.3 GB 15.0 GB
Too big Get file →
IQ3_XXS12.8 GB 15.5 GB
Too big Get file →
IQ3_XS13.7 GB 16.4 GB
Too big Get file →
Q3_K_S14.4 GB 17.0 GB
Too big Get file →
IQ3_S14.4 GB 17.1 GB
Too big Get file →
IQ3_M14.9 GB 17.6 GB
Too big Get file →
Q3_K_M16.0 GB 18.6 GB
Too big Get file →
Q3_K_L17.3 GB 20.0 GB
Too big Get file →
IQ4_XS17.7 GB 20.3 GB
Too big Get file →
Q4_018.7 GB 21.4 GB
Too big Get file →
Q4_K_S18.8 GB 21.4 GB
Too big Get file →
Q4_K_M19.8 GB 22.4 GB
Too big Get file →
Q4_120.6 GB 23.3 GB
Too big Get file →
Q5_K_S22.6 GB 25.3 GB
Too big Get file →
Q5_K_M23.2 GB 25.9 GB
Too big Get file →
Q6_K26.9 GB 29.5 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (7.32 GB, ~10 GB VRAM). For 12 GB VRAM, IQ2_S (9.95 GB, ~12.6 GB VRAM). For 16 GB VRAM, Q3_K_S (14.39 GB, ~17 GB VRAM). Estimates are approximate.

What GPU do you need for AesCode 32B?

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 (0.0 GB file, about 2.7 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ2_XXS (9.0 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XXS (12.8 GB file, about 15.5 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_1 (20.6 GB file, about 23.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (26.9 GB file, about 29.5 GB in use).

Which AesCode 32B quant should you choose?

Q4_K_M is the usual starting point for AesCode 32B: it balances file size and quality well. Here it is a 19.8 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 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

Architectureqwen3vl
Parameters32.8B
Layers64
Trained context262,144 tokens
KV cache (fp16)256 KB per token

Source

Quantized bymradermacher
FamilyAescode
Licenseapache-2.0
Downloads (HF)4,899
Last updated2026-10-15

Frequently asked questions about AesCode 32B

How much VRAM does AesCode 32B need?

About 22.4 GB at Q4_K_M with an 8K context window. That is the 19.8 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 AesCode 32B on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of AesCode 32B GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 7.3 GB, IQ1_M is 8.0 GB, IQ2_XXS is 9.0 GB, IQ2_XS is 10.0 GB, IQ2_S is 10.5 GB and 18 more.

What context length does AesCode 32B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). 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 AesCode 32B GGUF?

The files are on Hugging Face in the mradermacher/AesCode-32B-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 AesCode 32B 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.

Can I run AesCode 32B on 8 GB VRAM?

Use the IQ1_S quant; it requires about 10 GB VRAM at 8k context.

Does the model support vision input?

Yes, it is a vision‑language model but requires a compatible mmproj file.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of AesCode-32B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Aescode models

All Aescode →

Other medium models

All medium models →