ME

medgemma 1.5 4b it gguf q5 k m two stage

MedgemmaGGUF by DocUAUpdated 2026-02-18
Download on Hugging Face
Parameters3.88B
Context128K
Layers—
Architecturegemma3
Smallest quant0.1 GB
Quick answer

medgemma 1.5 4b it gguf q5 k m two stage needs about 0.6 GB of memory at F16 (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.1 GB (F16) to 2.8 GB (Q5_K_M).

medgemma 1.5 4b it gguf q5 k m two stage is a 3.88B-parameter Medgemma model in GGUF format, quantized by DocUA. Its trained context length is 128K tokens. The repository has 2 quant files, from 0.1 GB (F16) to 2.8 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F160.1 GB 0.6 GB
Fits Get file →
Q5_K_M2.8 GB 3.7 GB
Fits Get file →

What GPU do you need for medgemma 1.5 4b it gguf q5 k m two stage?

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: the best quant that fits is Q5_K_M (2.8 GB file, about 3.7 GB in use).

Which medgemma 1.5 4b it gguf q5 k m two stage quant should you choose?

F16 (0.1 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma3
Parameters3.88B
Trained context131,072 tokens

Source

Quantized byDocUA
FamilyMedgemma
Licenseother
Downloads (HF)68
Last updated2026-02-18

Frequently asked questions about medgemma 1.5 4b it gguf q5 k m two stage

How much VRAM does medgemma 1.5 4b it gguf q5 k m two stage need?

About 0.6 GB at F16 with an 8K context window. That is the 0.1 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 medgemma 1.5 4b it gguf q5 k m two stage on an 8 GB GPU?

Yes, with Q5_K_M: the 2.8 GB file needs about 3.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of medgemma 1.5 4b it gguf q5 k m two stage GGUF?

It depends on the quant: F16 is 0.1 GB, Q5_K_M is 2.8 GB.

What context length does medgemma 1.5 4b it gguf q5 k m two stage support?

The GGUF header lists a trained context length of 131,072 tokens (128K).

Where can I download medgemma 1.5 4b it gguf q5 k m two stage GGUF?

The files are on Hugging Face in the DocUA/medgemma-1.5-4b-it-gguf-q5-k-m-two-stage repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does medgemma 1.5 4b it gguf q5 k m two stage 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.

Other GGUFs of medgemma-1.5-4b-it

Similar models

Browse all →

More Medgemma models

All Medgemma →

Other small models

All small models →