EV

meituan EvoCUA 32B 20260105

EvocuaGGUF by spicyneuronUpdated 2026-01-21
Download on Hugging Face
Parameters32.8B
Context256K
Layers64
Architectureqwen3vl
Smallest quant12.8 GB
Quick answer

meituan EvoCUA 32B 20260105 needs about 22.7 GB of memory at Q4_K_XL (a 20.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 12.8 GB (Q2_K_XL) to 39.5 GB (Q8_K_XL). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

meituan EvoCUA 32B 20260105 is a 32.8B-parameter Evocua model in GGUF format, quantized by spicyneuron. Its trained context length is 256K tokens. The repository has 4 quant files, from 12.8 GB (Q2_K_XL) to 39.5 GB (Q8_K_XL).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K_XL12.8 GB 15.4 GB
Too big Get file →
Q4_K_XL20.1 GB 22.7 GB
Too big Get file →
Q6_K_XL29.0 GB 31.6 GB
Too big Get file →
Q8_K_XL39.5 GB 42.1 GB
Too big Get file →

What GPU do you need for meituan EvoCUA 32B 20260105?

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 Q2_K_XL (12.8 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_XL (20.1 GB file, about 22.7 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K_XL (29.0 GB file, about 31.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_K_XL (39.5 GB file, about 42.1 GB in use).

Which meituan EvoCUA 32B 20260105 quant should you choose?

Q4_K_XL (20.1 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q2_K_XL at 12.8 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

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 byspicyneuron
FamilyEvocua
Licenseapache-2.0
Downloads (HF)101
Last updated2026-01-21

Frequently asked questions about meituan EvoCUA 32B 20260105

How much VRAM does meituan EvoCUA 32B 20260105 need?

About 22.7 GB at Q4_K_XL with an 8K context window. That is the 20.1 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 meituan EvoCUA 32B 20260105 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of meituan EvoCUA 32B 20260105 GGUF?

It depends on the quant: Q2_K_XL is 12.8 GB, Q4_K_XL is 20.1 GB, Q6_K_XL is 29.0 GB, Q8_K_XL is 39.5 GB.

What context length does meituan EvoCUA 32B 20260105 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 meituan EvoCUA 32B 20260105 GGUF?

The files are on Hugging Face in the spicyneuron/meituan-EvoCUA-32B-20260105-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 meituan EvoCUA 32B 20260105 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 EvoCUA-32B-20260105

Similar models

Browse all →

More from spicyneuron

All by spicyneuron →

More Evocua models

All Evocua →

Other medium models

All medium models →