Model Gallery
Discover and install AI models from our curated collection
Find Your Perfect Model
Filter by Model Type
Browse by Tags
vllm-omni-wan2.2-t2v
Wan2.2-T2V-A14B via vLLM-Omni - Text-to-video generation model from Wan-AI. Generates high-quality videos from text prompts using a 14B parameter diffusion model.
Repository: localaiLicense: apache-2.0
vllm-omni-wan2.2-i2v
Wan2.2-I2V-A14B via vLLM-Omni - Image-to-video generation model from Wan-AI. Generates high-quality videos from images using a 14B parameter diffusion model.
Repository: localaiLicense: apache-2.0
arcee-ai_afm-4.5b
AFM-4.5B is a 4.5 billion parameter instruction-tuned model developed by Arcee.ai, designed for enterprise-grade performance across diverse deployment environments from cloud to edge. The base model was trained on a dataset of 8 trillion tokens, comprising 6.5 trillion tokens of general pretraining data followed by 1.5 trillion tokens of midtraining data with enhanced focus on mathematical reasoning and code generation. Following pretraining, the model underwent supervised fine-tuning on high-quality instruction datasets. The instruction-tuned model was further refined through reinforcement learning on verifiable rewards as well as for human preference. We use a modified version of TorchTitan for pretraining, Axolotl for supervised fine-tuning, and a modified version of Verifiers for reinforcement learning.
The development of AFM-4.5B prioritized data quality as a fundamental requirement for achieving robust model performance. We collaborated with DatologyAI, a company specializing in large-scale data curation. DatologyAI's curation pipeline integrates a suite of proprietary algorithms—model-based quality filtering, embedding-based curation, target distribution-matching, source mixing, and synthetic data. Their expertise enabled the creation of a curated dataset tailored to support strong real-world performance.
The model architecture follows a standard transformer decoder-only design based on Vaswani et al., incorporating several key modifications for enhanced performance and efficiency. Notable architectural features include grouped query attention for improved inference efficiency and ReLU^2 activation functions instead of SwiGLU to enable sparsification while maintaining or exceeding performance benchmarks.
The model available in this repo is the instruct model following supervised fine-tuning and reinforcement learning.
Repository: localaiLicense: aml
qwen3-30b-a1.5b-high-speed
This repo contains the full precision source code, in "safe tensors" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats. The source code can also be used directly.
This is a simple "finetune" of the Qwen's "Qwen 30B-A3B" (MOE) model, setting the experts in use from 8 to 4 (out of 128 experts).
This method close to doubles the speed of the model and uses 1.5B (of 30B) parameters instead of 3B (of 30B) parameters. Depending on the application you may want to use the regular model ("30B-A3B"), and use this model for simpler use case(s) although I did not notice any loss of function during routine (but not extensive) testing.
Example generation (Q4KS, CPU) at the bottom of this page using 4 experts / this model.
More complex use cases may benefit from using the normal version.
For reference:
Cpu only operation Q4KS (windows 11) jumps from 12 t/s to 23 t/s.
GPU performance IQ3S jumps from 75 t/s to over 125 t/s. (low to mid level card)
Context size: 32K + 8K for output (40k total)
Repository: localaiLicense: apache-2.0
nousresearch_hermes-4-14b
Hermes 4 14B is a frontier, hybrid-mode reasoning model based on Qwen 3 14B by Nous Research that is aligned to you.
Read the Hermes 4 technical report here: Hermes 4 Technical Report
Chat with Hermes in Nous Chat: https://chat.nousresearch.com
Training highlights include a newly synthesized post-training corpus emphasizing verified reasoning traces, massive improvements in math, code, STEM, logic, creativity, and format-faithful outputs, while preserving general assistant quality and broadly neutral alignment.
What’s new vs Hermes 3
Post-training corpus: Massively increased dataset size from 1M samples and 1.2B tokens to ~5M samples / ~60B tokens blended across reasoning and non-reasoning data.
Hybrid reasoning mode with explicit … segments when the model decides to deliberate, and options to make your responses faster when you want.
Reasoning that is top quality, expressive, improves math, code, STEM, logic, and even creative writing and subjective responses.
Schema adherence & structured outputs: trained to produce valid JSON for given schemas and to repair malformed objects.
Much easier to steer and align: extreme improvements on steerability, especially on reduced refusal rates.
Repository: localaiLicense: apache-2.0
planetoid_27b_v.2
This is a merge of pre-trained gemma3 language models
Goal of this merge was to create good uncensored gemma 3 model good for assistant and roleplay, with uncensored vision.
First, vision: i dont know is it normal, but it slightly hallucinate (maybe q3 is too low?), but lack any refusals and otherwise work fine. I used default gemma 3 27b mmproj.
Second, text: it is slow on my hardware, slower than 24b mistral, speed close to 32b QWQ. Model is smart even on q3, responses are adequate in length and are interesting to read. Model is quite attentive to context, tested up to 8k - no problems or degradation spotted. (beware of your typos, it will copy yours mistakes) Creative capabilities are good too, model will create good plot for you, if you let it. Model follows instructions fine, it is really good in "adventure" type of cards. Russian is supported, is not too great, maybe on higher quants is better. Refusals was not encountered.
However, i find this model not unbiased enough. It is close to neutrality, but i want it more "dark". Positivity highly depends on prompts. With good enough cards model can do wonders.
Tested on Q3_K_L, t 1.04.
Repository: localaiLicense: gemma
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 two variants: a 4B multimodal version and a 27B text-only version.
MedGemma 4B utilizes 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. Its LLM component is trained on a diverse set of medical data, including 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 has been trained exclusively on medical text and optimized for inference-time computation. MedGemma 27B is only available as an instruction-tuned model.
MedGemma variants have been evaluated on a range of clinically relevant benchmarks to illustrate their baseline performance. These include 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.
Repository: localaiLicense: gemma
medgemma-27b-text-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 two variants: a 4B multimodal version and a 27B text-only version.
MedGemma 4B utilizes 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. Its LLM component is trained on a diverse set of medical data, including 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 has been trained exclusively on medical text and optimized for inference-time computation. MedGemma 27B is only available as an instruction-tuned model.
MedGemma variants have been evaluated on a range of clinically relevant benchmarks to illustrate their baseline performance. These include 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.
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: gemma
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: gemma
l3.3-70b-magnum-v4-se
The Magnum v4 series is complete, but here's something a little extra I wanted to tack on as I wasn't entirely satisfied with the results of v4 72B. "SE" for Special Edition - this model is finetuned from meta-llama/Llama-3.3-70B-Instruct as an rsLoRA adapter. The dataset is a slightly revised variant of the v4 data with some elements of the v2 data re-introduced.
The objective, as with the other Magnum models, is to emulate the prose style and quality of the Claude 3 Sonnet/Opus series of models on a local scale, so don't be surprised to see "Claude-isms" in its output.
Repository: localaiLicense: llama3.3
nohobby_l3.3-prikol-70b-v0.5
99% of mergekit addicts quit before they hit it big.
Gosh, I need to create an org for my test runs - my profile looks like a dumpster.
What was it again? Ah, the new model.
Exactly what I wanted. All I had to do was yank out the cursed official DeepSeek distill and here we are.
From the brief tests it gave me some unusual takes on the character cards I'm used to. Just this makes it worth it imo. Also the writing is kinda nice.
Repository: localaiLicense: llama3.3
nohobby_l3.3-prikol-70b-extra
After banging my head against the wall some more - I actually managed to merge DeepSeek distill into my mess! Along with even more models (my hand just slipped, I swear)
The prose is better than in v0.5, but has a different feel to it, so I guess it's more of a step to the side than forward (hence the title EXTRA instead of 0.6).
The context recall may have improved, or I'm just gaslighting myself to think so.
And of course, since it now has DeepSeek in it - tags!
They kinda work out of the box if you add to the 'Start Reply With' field in ST - that way the model will write a really short character thought in it. However, if we want some OOC reasoning, things get trickier.
My initial thought was that this model could be instructed to use either only for {{char}}'s inner monologue or for detached analysis, but actually it would end up writing character thoughts most of the time anyway, and the times when it did reason stuff it threw the narrative out of the window by making it too formal and even adding some notes at the end.
Repository: localaiLicense: llama3.3
latitudegames_wayfarer-large-70b-llama-3.3
We’ve heard over and over from AI Dungeon players that modern AI models are too nice, never letting them fail or die. While it may be good for a chatbot to be nice and helpful, great stories and games aren’t all rainbows and unicorns. They have conflict, tension, and even death. These create real stakes and consequences for characters and the journeys they go on.
Similarly, great games need opposition. You must be able to fail, die, and may even have to start over. This makes games more fun!
However, the vast majority of AI models, through alignment RLHF, have been trained away from darkness, violence, or conflict, preventing them from fulfilling this role. To give our players better options, we decided to train our own model to fix these issues.
The Wayfarer model series are a set of adventure role-play models specifically trained to give players a challenging and dangerous experience.
We wanted to contribute back to the open source community that we’ve benefitted so much from so we open sourced a 12b parameter version version back in Jan. We thought people would love it but people were even more excited than we expected.
Due to popular request we decided to train a larger 70b version based on Llama 3.3.
Repository: localaiLicense: llama3.3
delta-vector_plesio-70b
A simple merge yet sovl in it's own way, This merge is inbetween Shimamura & Austral Winton, I wanted to give Austral a bit of shorter prose, So FYI for all the 10000+ Token reply lovers.
Thanks Auri for testing!
Using the Oh-so-great 0.2 Slerp merge weight with Winton as the Base.
Repository: localaiLicense: llama3.3
invisietch_l3.3-ignition-v0.1-70b
Ignition v0.1 is a Llama 3.3-based model merge designed for creative roleplay and fiction writing purposes. The model underwent a multi-stage merge process designed to optimise for creative writing capability, minimising slop, and improving coherence when compared with its constituent models.
The model shows a preference for detailed character cards and is sensitive to detailed system prompting. If you want a specific behavior from the model, try prompting for it directly.
Inferencing has been tested at fp8 and fp16, and both are coherent up to ~64k context.
Repository: localaiLicense: llama3.3
dolphin3.0-llama3.2-1b
Dolphin 3.0 is the next generation of the Dolphin series of instruct-tuned models. Designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases.
Dolphin aims to be a general purpose model, similar to the models behind ChatGPT, Claude, Gemini. But these models present problems for businesses seeking to include AI in their products.
They maintain control of the system prompt, deprecating and changing things as they wish, often causing software to break.
They maintain control of the model versions, sometimes changing things silently, or deprecating older models that your business relies on.
They maintain control of the alignment, and in particular the alignment is one-size-fits all, not tailored to the application.
They can see all your queries and they can potentially use that data in ways you wouldn't want. Dolphin, in contrast, is steerable and gives control to the system owner. You set the system prompt. You decide the alignment. You have control of your data. Dolphin does not impose its ethics or guidelines on you. You are the one who decides the guidelines.
Dolphin belongs to YOU, it is your tool, an extension of your will. Just as you are personally responsible for what you do with a knife, gun, fire, car, or the internet, you are the creator and originator of any content you generate with Dolphin.
Repository: localaiLicense: llama3.2
dolphin3.0-llama3.2-3b
Dolphin 3.0 is the next generation of the Dolphin series of instruct-tuned models. Designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases.
Dolphin aims to be a general purpose model, similar to the models behind ChatGPT, Claude, Gemini. But these models present problems for businesses seeking to include AI in their products.
They maintain control of the system prompt, deprecating and changing things as they wish, often causing software to break.
They maintain control of the model versions, sometimes changing things silently, or deprecating older models that your business relies on.
They maintain control of the alignment, and in particular the alignment is one-size-fits all, not tailored to the application.
They can see all your queries and they can potentially use that data in ways you wouldn't want. Dolphin, in contrast, is steerable and gives control to the system owner. You set the system prompt. You decide the alignment. You have control of your data. Dolphin does not impose its ethics or guidelines on you. You are the one who decides the guidelines.
Dolphin belongs to YOU, it is your tool, an extension of your will. Just as you are personally responsible for what you do with a knife, gun, fire, car, or the internet, you are the creator and originator of any content you generate with Dolphin.
Repository: localaiLicense: llama3.2
eximius_persona_5b
I wanted to create a model with an exceptional capacity for using varied speech patterns and fresh role-play takes. The model had to have a unique personality, not on a surface level but on the inside, for real. Unfortunately, SFT alone just didn't cut it. And I had only 16GB of VRAM at the time. Oh, and I wanted it to be small enough to be viable for phones and to be able to give a fight to larger models while at it. If only there was a magical way to do it.
Merges. Merges are quite unique. In the early days, they were considered "fake." Clearly, there's no such thing as merges. Where are the papers? No papers? Then it's clearly impossible. "Mathematically impossible." Simply preposterous. To mix layers and hope for a coherent output? What nonsense!
And yet, they were real. Undi95 made some of the earliest merges I can remember, and the "LLAMA2 Era" was truly amazing and innovative thanks to them. Cool stuff like Tiefighter was being made, and eventually the time tested Midnight-Miqu-70B (v1.5 is my personal favorite).
Merges are an interesting thing, as they affect LLMs in a way that is currently impossible to reproduce using SFT (or any 'SOTA' technique). One of the plagues we have today, while we have orders of magnitude smarter LLMs, is GPTisms and predictability. Merges can potentially 'solve' that. How? In short, if you physically tear neurons (passthrough brain surgery) while you somehow manage to keep the model coherent enough, and if you're lucky, it can even follows instructions- then magical stuff begins to happen.
Repository: localaiLicense: llama3.2
llama3.1-8b-chinese-chat
llama3.1-8B-Chinese-Chat is an instruction-tuned language model for Chinese & English users with various abilities such as roleplaying & tool-using built upon the Meta-Llama-3.1-8B-Instruct model. Developers: [Shenzhi Wang](https://shenzhi-wang.netlify.app)*, [Yaowei Zheng](https://github.com/hiyouga)*, Guoyin Wang (in.ai), Shiji Song, Gao Huang. (*: Equal Contribution) - License: [Llama-3.1 License](https://huggingface.co/meta-llama/Meta-Llla...
m-3.1-8B/blob/main/LICENSE) - Base Model: Meta-Llama-3.1-8B-Instruct - Model Size: 8.03B - Context length: 128K(reported by [Meta-Llama-3.1-8B-Instruct model](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct), untested for our Chinese model)
Repository: localaiLicense: llama3.1
l3.1-70b-glitz-v0.2-i1
this is an experimental l3.1 70b finetuning run... that crashed midway through. however, the results are still interesting, so i wanted to publish them :3
Repository: localaiLicense: llama3.1
Page
1
of many