ME

Medgemma 27b Text It

MedgemmaGGUF by second-stateUpdated 2025-05-22
Download on Hugging Face
Parameters27B
Context128K
Layers62
Architecturegemma3
Smallest quant10.5 GB
Quick answer

Medgemma 27b Text It needs about 21.2 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 13 quants, from 10.5 GB (Q2_K) to 54.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 16.6 GB.

Medgemma 27b Text It – 27B parameter Gemini‑style model

Medgemma 27b Text It is a 27B parameter model based on the gemma3 architecture. It supports vision and text tasks with a context size of 131072 tokens. The model is available in multiple GGUF quantizations.

Good at

  • Vision and text integration
  • Large context handling
  • High parameter count

Limits

  • No official license details
  • Requires 896x896 image normalization
  • Large VRAM for higher quants

Best for

  • Multimodal content creation
  • Long‑form document analysis
  • Complex image‑text reasoning

Who it’s for. Developers and researchers needing a high‑capacity multimodal model for local deployment. Suitable for environments with sufficient GPU memory and the ability to run llama.cpp or LlamaEdge.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K10.5 GB 15.2 GB
Too big Get file →
Q3_K_S12.2 GB 16.8 GB
Too big Get file →
Q3_K_M13.4 GB 18.1 GB
Too big Get file →
Q3_K_L14.5 GB 19.2 GB
Too big Get file →
Q4_015.6 GB 20.2 GB
Too big Get file →
Q4_K_S15.7 GB 20.3 GB
Too big Get file →
Q4_K_M16.5 GB 21.2 GB
Too big Get file →
Q5_018.8 GB 23.4 GB
Too big Get file →
Q5_K_S18.8 GB 23.4 GB
Too big Get file →
Q5_K_M19.3 GB 23.9 GB
Too big Get file →
Q6_K22.2 GB 26.8 GB
Too big Get file →
Q8_028.7 GB 33.4 GB
Too big Get file →
F1654.0 GB (2 parts) 58.7 GB
Too big Get file →

For 8 GB VRAM, use Q4_K (15.2 GB memory at 8k context). For 12 GB VRAM, Q5_K_S (23.4 GB memory) is too large; consider Q4_K_M (21.2 GB). For 16 GB VRAM, Q5_K_M (23.9 GB) is still high; Q4_K_M or Q4_K_S are safer. Memory estimates are approximate.

What GPU do you need for Medgemma 27b Text It?

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 (10.5 GB file, about 15.2 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (19.3 GB file, about 23.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (22.2 GB file, about 26.8 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (28.7 GB file, about 33.4 GB in use).

Which Medgemma 27b Text It quant should you choose?

Q4_K_M is the usual starting point for Medgemma 27b Text It: it balances file size and quality well. Here it is a 16.5 GB file.

The Q8_0 file is 28.7 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 10.5 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

Architecturegemma3
Parameters27B
Layers62
Trained context131,072 tokens
KV cache (fp16)496 KB per token

Source

Quantized bysecond-state
FamilyMedgemma
Licenseother
Downloads (HF)791
Last updated2025-05-22

Frequently asked questions about Medgemma 27b Text It

How much VRAM does Medgemma 27b Text It need?

About 21.2 GB at Q4_K_M with an 8K context window. That is the 16.5 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 Medgemma 27b Text It on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Medgemma 27b Text It GGUF?

It depends on the quant: Q2_K is 10.5 GB, Q3_K_S is 12.2 GB, Q3_K_M is 13.4 GB, Q3_K_L is 14.5 GB, Q4_0 is 15.6 GB, Q4_K_S is 15.7 GB and 7 more.

What context length does Medgemma 27b Text It support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.2 GB at 8K and 16.6 GB at 32K.

Where can I download Medgemma 27b Text It GGUF?

The files are on Hugging Face in the second-state/medgemma-27b-text-it-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 Medgemma 27b Text It 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 Medgemma 27b Text It on 8 GB VRAM?

Only the Q2_K quant (15.2 GB memory at 8k context) is close; 8 GB VRAM is insufficient for any quant.

Does the model support image input?

Yes, but images must be normalized to 896x896 and encoded to 256 tokens each.

What context size does the model support?

The model was trained with a context of 131072 tokens.

Other GGUFs of medgemma-27b-text-it

Similar models

Browse all →

More from second-state

All by second-state →

More Medgemma models

All Medgemma →

Other medium models

All medium models →