MA

Mark VL 2.2B

MarkGGUF by miceworksUpdated 2026-11-01
Download on Hugging Face
Parameters2.17B
Context256K
Layers36
Architectureqwen3vl
Smallest quant1.2 GB
Quick answer

Mark VL 2.2B needs about 4.2 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 1.2 GB (IQ4_NL) to 2.5 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Mark VL 2.2B is a 2.17B-parameter Mark model in GGUF format, quantized by miceworks. Its trained context length is 256K tokens. The repository has 2 quant files, from 1.2 GB (IQ4_NL) to 2.5 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_NL1.2 GB 2.9 GB
Fits Get file →
Q4_K_M2.5 GB 4.2 GB
Fits Get file →

What GPU do you need for Mark VL 2.2B?

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 IQ4_NL (1.2 GB file, about 2.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K_M (2.5 GB file, about 4.2 GB in use).

Which Mark VL 2.2B quant should you choose?

Q4_K_M is the usual starting point for Mark VL 2.2B: it balances file size and quality well. Here it is a 2.5 GB file.

If memory is tight, the smallest file is IQ4_NL at 1.2 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3vl
Parameters2.17B
Layers36
Trained context262,144 tokens
KV cache (fp16)144 KB per token

Source

Quantized bymiceworks
FamilyMark
Licenseagpl-3.0
Downloads (HF)387
Last updated2026-11-01

Frequently asked questions about Mark VL 2.2B

How much VRAM does Mark VL 2.2B need?

About 4.2 GB at Q4_K_M with an 8K context window. That is the 2.5 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 Mark VL 2.2B on an 8 GB GPU?

Yes, with Q4_K_M: the 2.5 GB file needs about 4.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Mark VL 2.2B GGUF?

It depends on the quant: IQ4_NL is 1.2 GB, Q4_K_M is 2.5 GB.

What context length does Mark VL 2.2B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download Mark VL 2.2B GGUF?

The files are on Hugging Face in the miceworks/Mark-VL-2.2B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Mark VL 2.2B use?

Hugging Face lists the license as agpl-3.0. 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 miceworks

All by miceworks →

More Mark models

All Mark →

Other tiny models

All tiny models →