Medgemma 4B · Ollama

medgemma1.5

MedGemma 1.5 4B is an updated version of the MedGemma 4B model.

154.1K Pulls 5 Tags Updated 4 months ago

MedAIBase/MedGemma1.5

MedGemma 1.5 4B is an updated version of the MedGemma 1 4B model, delivers improved accuracy on medical text reasoning and modest improvement on standard 2D image interpretation compared to MedGemma 1 4B. The 4b-it-q4_0 has overfitting! Avoid it.

4b

6,151 Pulls 5 Tags Updated 7 months ago

dcarrascosa/medgemma-1.5-4b-it

This repo packages Google’s google/medgemma-1.5-4b-it (MedGemma 1.5, 4B, instruction-tuned, multimodal) for Ollama, exposing vision + text inference and common Ollama features (structured JSON output, tool calling via your app, etc.)

vision

2,161 Pulls 3 Tags Updated 6 months ago

AntAngelMed/MedGemma1.5

MedGemma 1.5 4B is an updated version of the MedGemma 1 4B model, delivers improved accuracy on medical text reasoning and modest improvement on standard 2D image interpretation compared to MedGemma 1 4B. The 4b-it-q4_0 has overfitting! Avoid it.

4b

238 Pulls 5 Tags Updated 7 months ago

leniartekpiotr/EyeGemma

MedGemma-1.5-4B-it model fine tuned the with the biggest public retinal diabetic dataset (haideraltahan/wds_diabetic_retinopathy) on Hugging Face to better triage Diabetic Retinopathy.

vision

42 Pulls 1 Tag Updated 5 months ago

jordimurgo/medgemma1.5-thinking

MedGemma 1.5 4.3B Q4_K_M with native Ollama thinking separation, vision support, deterministic decoding, and unchanged official weights and tokenizer.

vision thinking

39 Pulls 1 Tag Updated 1 month ago

aadide/medgemma-1.5-4b-it-Q4_K_S

https://research.google/blog/next-generation-medical-image-interpretation-with-medgemma-15-and-medical-speech-to-text-with-medasr/

423 Pulls 1 Tag Updated 7 months ago

maxwellb/gemma4-12b-it-dn

Quantized GGUF of hf.co/DuoNeural/Gemma4-12B-IT-Abliterated

vision tools thinking

558 Pulls 3 Tags Updated 2 months ago

maxwellb/gemma4-12b-it-oym

Quantized GGUF of hf.co/OpenYourMind/gemma-4-12B-it-abliterated-uncensored

vision tools thinking

13.9K Pulls 3 Tags Updated 2 months ago

mannix/gemma4-98e-v5-coder

Pruned to 98 experts gemma-4 a4b 26b v5-coder. Best 20b coder model overall

tools thinking

468 Pulls 31 Tags Updated 3 months ago

mo-shakib/gemma4-e4b-uncensored

An uncensored Gemma 4 8B model for local inference with zero built-in refusal behavior

vision tools thinking

3,562 Pulls 1 Tag Updated 1 month ago

huihui_ai/huihui-4

Huihui4-8B-A4B is a lightweight MoE (Mixture of Experts) conversational model optimized from Google's gemma-4-26B-A4B-it architecture

vision tools thinking 8b

3,162 Pulls 4 Tags Updated 4 months ago

maxwell1500/psycho

A local-first psychology assistant fine-tuned from Gemma 4 on real therapy dialogues. Two model series: E2B (2.3B, 3.3–5.0 GB) and 12B (11.96B, 6.2–11.8 GB). 128K context. Legal Notice: Not a substitute for professional care.

tools thinking 12b

627 Pulls 11 Tags Updated 2 months ago

su_robin/gemma-4-E4B-it-Q4_K_M

4-bit K-quntized version of google/gemma-4-E4B-it. Generated using llama.cpp

tools thinking

2,954 Pulls 1 Tag Updated 4 months ago

mannix/gemma4-98e-v7-coder

An even more improved version of Gemma-4 98e coder variant, the best 20b coder

vision tools thinking

1,318 Pulls 27 Tags Updated 1 month ago

fauxpaslife/gemma-4-E4B-it-textonly-sysprmpt-Q4_K_M

A structurally extracted, text-only iteration of Google's multimodal gemma-4-E4B-it model. Vision and audio encoders have been fully decoupled to minimize VRAM footprint for text-centric workloads. System Prompt to address lost abilities.

tools thinking

603 Pulls 1 Tag Updated 4 months ago

jikepjikep_16HEX/gemma-4-26b-nightshift-heretic-uncensored-a4b-moe-q4

😈 Uncensored Gemma 4 26B (A4B MoE) for Ollama. 👁️ Native Vision, 🛠️ Tool Calling, GGUF, Rust 1.98.0 , Linux, Windows AI Coding Agents and multimodal local AI development. 🚀

vision tools thinking

1,333 Pulls 1 Tag Updated 1 week ago

igorls/gemma4-e4b-classifier

A modality-stripped variant of google/gemma-4-E4B-it for text-only classification, entity extraction, and structured-memory extraction. The vision encoder (150M params) and audio encoder (300M params) are removed; the text path is unchanged.

tools thinking

323 Pulls 3 Tags Updated 3 months ago

os-w/open-assistans-v3-coder

This is an AI model based on the Gemma4 Model Family, but designed to address issues such as sycophancy or unnecessary praise that may arise in AI models. (It has the ability to reason.) This has no connection to the OpenAssistans project.

vision tools thinking e2b e4b 12b 26b 31b

84 Pulls 6 Tags Updated 1 month ago

os-w/open-assistans-v3-reasoning

This is an AI model based on the Gemma4 Model Family, but designed to address issues such as sycophancy or unnecessary praise that may arise in AI models. (It has the ability to reason.) This has no connection to the OpenAssistans project.

vision tools thinking e2b e4b 12b 26b 31b

19 Pulls 6 Tags Updated 1 month ago