Medgemma GGUF models

194 GGUF models in the Medgemma family, quantized by 112 uploaders. Sizes run from 12M to 28.4B parameters. The longest trained context is 128K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
ME
Medgemma-4B-It
Medgemma · unsloth
Params3.88B
Context128K
Q4_K_M2.5 GB
ReasoningVision
ME
Medgemma-1.5-4B-It
Medgemma · unsloth
Params3.88B
Context128K
Q4_K_M2.5 GB
ReasoningVision
ME
Medgemma-27B-Text-It
Medgemma · unsloth
Params27B
Context128K
Q4_K_M16.5 GB
ReasoningVision
ME
Medgemma-27B-It
Medgemma · unsloth
Params27B
Context128K
Q4_K_M16.5 GB
EmbeddingVision
ME
Medgemma 27b It
Medgemma · bartowski
Params27B
Context128K
Q4_K_M16.5 GB
EmbeddingVision
ME
Medgemma 4b It
Medgemma · bartowski
Params3.88B
Context128K
Q4_K_M2.5 GB
ReasoningVision
ME
Medgemma 27b Text It Abliterated
Medgemma · mradermacher
Params27B
Context128K
Q4_K_M16.5 GB
GGUF
ME
MedGemma GRPO
Medgemma · mradermacher
Params3.88B
Context128K
Q4_K_M2.5 GB
Reasoning
ME
Medgemma 4b It
Medgemma · second-state
Params3.88B
Context128K
Q4_K_M2.5 GB
ReasoningVision
ME
Medgemma 27b It
Medgemma · mradermacher
Params27B
Context128K
Q4_K_M16.5 GB
EmbeddingVision
ME
Google_Medgemma 4b It
Medgemma · lmstudio-community
Params3.88B
Context128K
Q4_K_M2.5 GB
Vision
ME
Medgemma 27b Abliterated Multimodal
Medgemma · mradermacher
Params27B
Context128K
Q4_K_M16.5 GB
GGUF
ME
Medgemma 1.5 4b It
Medgemma · mradermacher
Params3.88B
Context128K
Q4_K_M2.5 GB
ReasoningVision
ME
Medgemma 27b Text It
Medgemma · second-state
Params27B
Context128K
Q4_K_M16.5 GB
Vision
ME
Google_Medgemma 27b Text It
Medgemma · lmstudio-community
Params27B
Context128K
Q4_K_M16.5 GB
GGUF
ME
MedGemma FineTuned
Medgemma · Aakash010
Params3.88B
Context128K
Q4_K_M2.5 GB
Vision
ME
Google.Medgemma 4b It
Medgemma · DevQuasar
Params3.88B
Context128K
Q4_K_M2.5 GB
Vision
ME
Medgemma 27b It
Medgemma · mradermacher
Params27B
Context128K
Q4_K_M16.5 GB
EmbeddingVision
ME
Medgemma 27b Text It
Medgemma · gaianet
Params27B
Context128K
Q4_K_M16.5 GB
Vision
ME
Medgemma3 Thinking
Medgemma · mradermacher
Params27B
Context128K
Q4_K_M16.5 GB
Reasoning
ME
Medgemma 27b It Abliterated
Medgemma · mradermacher
Params28.4B
Context128K
Q4_K_M17.3 GB
GGUF
ME
Medgemma 27b Abliterated Multimodal
Medgemma · mradermacher
Params27B
Context128K
Q4_K_M16.5 GB
Vision
ME
Medgemma Nuslerp 27b
Medgemma · mradermacher
Params27B
Context128K
Q4_K_M16.5 GB
GGUF
ME
Medgemma 27b Text It
Medgemma · mradermacher
Params27B
Context128K
Q4_K_M16.5 GB
Reasoning
ME
Medgemma 27b It Abliterated
Medgemma · mradermacher
Params28.4B
Context128K
Q4_K_M17.3 GB
GGUF
ME
Medgemma 4b It Heretic
Medgemma · mradermacher
Params3.88B
Context128K
Q4_K_M2.5 GB
ReasoningVision
ME
Medgemma 27b Text It
Medgemma · mradermacher
Params27B
Context128K
Q4_K_M16.5 GB
Reasoning
ME
Google.Medgemma 27b Text It
Medgemma · DevQuasar
Params27B
Context128K
Q4_K_M16.5 GB
GGUF
ME
Medgemma-4B-It
Medgemma · XythicK
Params3.88B
Context128K
Q4_K_M2.5 GB
Vision
ME
Medgemma 4b It Abliterated
Medgemma · mradermacher
Params3.88B
Context128K
Q4_K_M2.5 GB
GGUF

About the Medgemma GGUF models

Medgemma is represented on ggufmodels.com by 194 GGUF models, quantized by 112 uploaders on Hugging Face. The most downloaded are Medgemma-4B-It, Medgemma-1.5-4B-It and Medgemma-27B-Text-It. Parameter counts run from 12M to 28.4B, and the longest trained context window is 128K tokens.

A Q4_K_M file of a Medgemma model is between 2.5 to 17.3 GB, which is the quant most people start with. Most files come from mradermacher (36), unsloth (4) and bolmu321 (4). The quants you will meet most often are Q4_K_M (119), Q5_K_M (72), Q8_0 (68) and Q6_K (66), where the number is how many models offer that quant.

Frequently asked questions

Which Medgemma GGUF should I download?

The most downloaded Medgemma GGUF here is Medgemma-4B-It. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a Medgemma model need?

Q4_K_M files of Medgemma models on this site range from 2.5 to 17.3 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do Medgemma GGUF files come from?

The most common quantizers here are mradermacher, unsloth and bolmu321. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing