Filter by type:
Filter by tags:
gemma-3-12b-it
google/gemma-3-12b-it is an open-source, state-of-the-art, lightweight, multimodal model built from the same research and technology used to create the Gemini models. It is capable of handling text and image input and generating text output. It has a large context window of 128K tokens and supports over 140 languages. The 12B variant has been fine-tuned using the instruction-tuning approach. Gemma 3 models are suitable for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes them deployable in environments with limited resources such as laptops, desktops, or your own cloud infrastructure.
Repository: localaiLicense: gemma
gemma-3-4b-it
Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions. Gemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone. Gemma-3-4b-it is a 4 billion parameter model.
Repository: localaiLicense: gemma
gemma-3-1b-it
google/gemma-3-1b-it is a large language model with 1 billion parameters. It is part of the Gemma family of open, state-of-the-art models from Google, built from the same research and technology used to create the Gemini models. Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. These models have multilingual support in over 140 languages, and are available in more sizes than previous versions. They are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone.
Repository: localaiLicense: gemma
gemma-3-12b-it-qat
This model corresponds to the 12B instruction-tuned version of the Gemma 3 model in GGUF format using Quantization Aware Training (QAT). The GGUF corresponds to Q4_0 quantization.
Thanks to QAT, the model is able to preserve similar quality as bfloat16 while significantly reducing the memory requirements to load the model.
You can find the half-precision version here.
Repository: localaiLicense: gemma
gemma-3-4b-it-qat
This model corresponds to the 4B instruction-tuned version of the Gemma 3 model in GGUF format using Quantization Aware Training (QAT). The GGUF corresponds to Q4_0 quantization.
Thanks to QAT, the model is able to preserve similar quality as bfloat16 while significantly reducing the memory requirements to load the model.
You can find the half-precision version here.
Repository: localaiLicense: gemma
gemma-3-27b-it-qat
This model corresponds to the 27B instruction-tuned version of the Gemma 3 model in GGUF format using Quantization Aware Training (QAT). The GGUF corresponds to Q4_0 quantization.
Thanks to QAT, the model is able to preserve similar quality as bfloat16 while significantly reducing the memory requirements to load the model.
You can find the half-precision version here.
Repository: localaiLicense: gemma
qgallouedec_gemma-3-27b-it-codeforces-sft
This model is a fine-tuned version of google/gemma-3-27b-it on the open-r1/codeforces-cots dataset. It has been trained using TRL.
Repository: localaiLicense: gemma
mlabonne_gemma-3-27b-it-abliterated
This is an uncensored version of google/gemma-3-27b-it created with a new abliteration technique. See this article to know more about abliteration.
Repository: localaiLicense: gemma
mlabonne_gemma-3-12b-it-abliterated
This is an uncensored version of google/gemma-3-12b-it created with a new abliteration technique. See this article to know more about abliteration.
Repository: localaiLicense: gemma
mlabonne_gemma-3-4b-it-abliterated
This is an uncensored version of google/gemma-3-4b-it created with a new abliteration technique. See this article to know more about abliteration.
Repository: localaiLicense: gemma
huihui-ai_gemma-3-1b-it-abliterated
This is an uncensored version of google/gemma-3-1b-it created with abliteration (see remove-refusals-with-transformers to know more about it).
This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens
Repository: localaiLicense: gemma
burtenshaw_gemmacoder3-12b
This model is a fine-tuned version of google/gemma-3-12b-it on the open-r1/codeforces-cots dataset. It has been trained using TRL.
Repository: localaiLicense: gemma
google-gemma-3-27b-it-qat-q4_0-small
This is a requantized version of https://huggingface.co/google/gemma-3-27b-it-qat-q4_0-gguf. The official QAT weights released by google use fp16 (instead of Q6_K) for the embeddings table, which makes this model take a significant extra amount of memory (and storage) compared to what Q4_0 quants are supposed to take. Requantizing with llama.cpp achieves a very similar result. Note that this model ends up smaller than the Q4_0 from Bartowski. This is because llama.cpp sets some tensors to Q4_1 when quantizing models to Q4_0 with imatrix, but this is a static quant. The perplexity score for this one is even lower with this model compared to the original model by Google, but the results are within margin of error, so it's probably just luck. I also fixed the control token metadata, which was slightly degrading the performance of the model in instruct mode.
Repository: localaiLicense: gemma
gemma-3-12b-fornaxv.2-qat-cot
This model is an experiment to try to produce a strong smaller thinking model capable of fitting in an 8GiB consumer graphics card with generalizeable reasoning capabilities. Most other open source thinking models, especially on the smaller side, fail to generalize their reasoning to tasks other than coding or math due to an overly large focus on GRPO zero for CoT which is only applicable for coding and math.
Instead of using GRPO, this model aims to SFT a wide variety of high quality, diverse reasoning traces from Deepseek R1 onto Gemma 3 to force the model to learn to effectively generalize its reasoning capabilites to a large number of tasks as an extension of the LiMO paper's approach to Math/Coding CoT. A subset of V3 O3/24 non-thinking data was also included for improved creativity and to allow the model to retain it's non-thinking capabilites.
Training off the QAT checkpoint allows for this model to be used without a drop in quality at Q4_0, requiring only ~6GiB of memory.
Thinking Mode
Similar to the Qwen 3 model line, Gemma Fornax can be used with or without thinking mode enabled.
To enable thinking place /think in the system prompt and prefill \n for thinking mode.
To disable thinking put /no_think in the system prompt.
Repository: localaiLicense: gemma
gemma-3n-e4b-it
Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3n models are designed for efficient execution on low-resource devices. They are capable of multimodal input, handling text, image, video, and audio input, and generating text outputs, with open weights for pre-trained and instruction-tuned variants. These models were trained with data in over 140 spoken languages.
Gemma 3n models use selective parameter activation technology to reduce resource requirements. This technique allows the models to operate at an effective size of 2B and 4B parameters, which is lower than the total number of parameters they contain. For more information on Gemma 3n's efficient parameter management technology, see the Gemma 3n page.
Repository: localaiLicense: gemma
huihui-ai_huihui-gemma-3n-e4b-it-abliterated
This is an uncensored version of google/gemma-3n-E4B-it created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.
It was only the text part that was processed, not the image part. After abliterated, it seems like more output content has been opened from a magic box.
Repository: localaiLicense: gemma
google_medgemma-4b-it
MedGemma is a collection of Gemma 3 variants that are trained for performance on medical text and image comprehension. Developers can use MedGemma to accelerate building healthcare-based AI applications. MedGemma currently comes in three variants: a 4B multimodal version and 27B text-only and multimodal versions.
Both MedGemma multimodal versions utilize a SigLIP image encoder that has been specifically pre-trained on a variety of de-identified medical data, including chest X-rays, dermatology images, ophthalmology images, and histopathology slides. Their LLM components are trained on a diverse set of medical data, including medical text, medical question-answer pairs, FHIR-based electronic health record data (27B multimodal only), radiology images, histopathology patches, ophthalmology images, and dermatology images.
MedGemma 4B is available in both pre-trained (suffix: -pt) and instruction-tuned (suffix -it) versions. The instruction-tuned version is a better starting point for most applications. The pre-trained version is available for those who want to experiment more deeply with the models.
MedGemma 27B multimodal has pre-training on medical image, medical record and medical record comprehension tasks. MedGemma 27B text-only has been trained exclusively on medical text. Both models have been optimized for inference-time computation on medical reasoning. This means it has slightly higher performance on some text benchmarks than MedGemma 27B multimodal. Users who want to work with a single model for both medical text, medical record and medical image tasks are better suited for MedGemma 27B multimodal. Those that only need text use-cases may be better served with the text-only variant. Both MedGemma 27B variants are only available in instruction-tuned versions.
MedGemma variants have been evaluated on a range of clinically relevant benchmarks to illustrate their baseline performance. These evaluations are based on both open benchmark datasets and curated datasets. Developers can fine-tune MedGemma variants for improved performance. Consult the Intended Use section below for more details.
MedGemma is optimized for medical applications that involve a text generation component. For medical image-based applications that do not involve text generation, such as data-efficient classification, zero-shot classification, or content-based or semantic image retrieval, the MedSigLIP image encoder is recommended. MedSigLIP is based on the same image encoder that powers MedGemma.
Repository: localaiLicense: health-ai-developer-foundations
google_medgemma-27b-it
MedGemma is a collection of Gemma 3 variants that are trained for performance on medical text and image comprehension. Developers can use MedGemma to accelerate building healthcare-based AI applications. MedGemma currently comes in three variants: a 4B multimodal version and 27B text-only and multimodal versions.
Both MedGemma multimodal versions utilize a SigLIP image encoder that has been specifically pre-trained on a variety of de-identified medical data, including chest X-rays, dermatology images, ophthalmology images, and histopathology slides. Their LLM components are trained on a diverse set of medical data, including medical text, medical question-answer pairs, FHIR-based electronic health record data (27B multimodal only), radiology images, histopathology patches, ophthalmology images, and dermatology images.
MedGemma 4B is available in both pre-trained (suffix: -pt) and instruction-tuned (suffix -it) versions. The instruction-tuned version is a better starting point for most applications. The pre-trained version is available for those who want to experiment more deeply with the models.
MedGemma 27B multimodal has pre-training on medical image, medical record and medical record comprehension tasks. MedGemma 27B text-only has been trained exclusively on medical text. Both models have been optimized for inference-time computation on medical reasoning. This means it has slightly higher performance on some text benchmarks than MedGemma 27B multimodal. Users who want to work with a single model for both medical text, medical record and medical image tasks are better suited for MedGemma 27B multimodal. Those that only need text use-cases may be better served with the text-only variant. Both MedGemma 27B variants are only available in instruction-tuned versions.
MedGemma variants have been evaluated on a range of clinically relevant benchmarks to illustrate their baseline performance. These evaluations are based on both open benchmark datasets and curated datasets. Developers can fine-tune MedGemma variants for improved performance. Consult the Intended use section below for more details.
MedGemma is optimized for medical applications that involve a text generation component. For medical image-based applications that do not involve text generation, such as data-efficient classification, zero-shot classification, or content-based or semantic image retrieval, the MedSigLIP image encoder is recommended. MedSigLIP is based on the same image encoder that powers MedGemma.
Repository: localaiLicense: health-ai-developer-foundations
yanolja_yanoljanext-rosetta-12b-2510
This model is a fine-tuned version of google/gemma-3-12b-pt. As it is intended solely for text generation, we have extracted and utilized only the Gemma3ForCausalLM component from the original architecture.
Unlike our previous EEVE models, this model does not feature an expanded tokenizer. Base Model: google/gemma-3-12b-pt
This model is a 12-billion parameter, decoder-only language model built on the Gemma3 architecture and fine-tuned by Yanolja NEXT. It is specifically designed to translate structured data (JSON format) while preserving the original data structure.
The model was trained on a multilingual dataset covering the following languages equally:
Arabic
Bulgarian
Chinese
Czech
Danish
Dutch
English
Finnish
French
German
Greek
Gujarati
Hebrew
Hindi
Hungarian
Indonesian
Italian
Japanese
Korean
Persian
Polish
Portuguese
Romanian
Russian
Slovak
Spanish
Swedish
Tagalog
Thai
Turkish
Ukrainian
Vietnamese
While optimized for these languages, it may also perform effectively on other languages supported by the base Gemma3 model.
Repository: localaiLicense: gemma
rombos-llm-70b-llama-3.3
You know the drill by now.
Here is the paper. Have fun.
https://docs.google.com/document/d/1OjbjU5AOz4Ftn9xHQrX3oFQGhQ6RDUuXQipnQ9gn6tU/edit?usp=sharing
Repository: localaiLicense: llama3.3
gemma-4-e2b-it:sglang-mtp
Google Gemma 4 E2B-IT served by SGLang with Multi-Token Prediction
(MTP) speculative decoding. The companion drafter
google/gemma-4-E2B-it-assistant lets the target accept several
tokens per step. Flags are a 1:1 transcription of the SGLang
cookbook's MTP command (NEXTN algorithm, num_steps=5,
num_draft_tokens=6, eagle_topk=1, mem_fraction_static=0.85). The
E2B variant has 5B total / 2B effective parameters and targets the
smaller end of consumer GPUs.
Repository: localaiLicense: gemma
Page 1