Chroma-GGUF
Clybius基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗DISCOVER & COMPARE
Explore AI models 84991
resnet18-eurosat
cm93基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Image→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗resnet50-eurosat
cm93基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Image→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗bloomz-560m-nli
cmarkeaWe introduce the Bloomz-560m-NLI model, fine-tuned from the Bloomz-560m-chat-dpo foundation model. This model is trained on a Natural Language Inference (NLI) task in a language-agnostic manner. The NLI task involves determining the semantic relationship between a hypothesis and a set of premises, often expressed as pairs of sentences. The goal is to predict textual entailment (does sentence A imply/contradict/neither sentence B?) and is a classification task (given two sentences, predict one of the three labels). If sentence A is called *premise*, and sentence B is called *hypothesis*, then the goal of the modelization is to estimate the following: $$P(premise=c\in\{contradiction, entailment, neutral\}\vert hypothesis)$$ It should be noted that hypotheses and premises are randomly chosen between English and French, with each language combination representing a probability of 25%.
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗detr-layout-detection
cmarkea基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Input Image→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗distilcamembert-base
cmarkeaWe present a distillation version of the well named CamemBERT, a RoBERTa French model version, alias DistilCamemBERT. The aim of distillation is to drastically reduce the complexity of the model while preserving the performances. The proof of concept is shown in the DistilBERT paper and the code used for the training is inspired by the code of DistilBERT. The training for the distilled model (student model) is designed to be the closest as possible to the original model (teacher model). To perform this the loss function is composed of 3 parts: * DistilLoss: a distillation loss which measures the silimarity between the probabilities at the outputs of the student and teacher models with a cross-entropy loss on the MLM task ; * CosineLoss: a cosine embedding loss. This loss function is applied on the last hidden layers of student and teacher models to guarantee a collinearity between them ; * MLMLoss: and finaly a Masked Language Modeling (MLM) task loss to perform the student model with the original task of the teacher model. The final loss function is a combination of these three losses functions. We use the following ponderation:
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗distilcamembert-base-ner
cmarkeaWe present DistilCamemBERT-NER, which is DistilCamemBERT fine-tuned for the NER (Named Entity Recognition) task for the French language. The work is inspired by Jean-Baptiste/camembert-ner based on the CamemBERT model. The problem of the modelizations based on CamemBERT is at the scaling moment, for the production phase, for example. Indeed, inference cost can be a technological issue. To counteract this effect, we propose this modelization which **divides the inference time by two** with the same consumption power thanks to DistilCamemBERT. This model performance is compared to 2 reference models (see below) with the metric f1 score. For the mean inference time measure, an AMD Ryzen 5 4500U @ 2.3GHz with 6 cores was used:
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗distilcamembert-base-nli
cmarkea基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗We present DistilCamemBERT-Sentiment, which is DistilCamemBERT fine-tuned for the sentiment analysis task for the French language. This model is built using two datasets: Amazon Reviews and Allociné.fr to minimize the bias. Indeed, Amazon reviews are similar in messages and relatively shorts, contrary to Allociné critics, who are long and rich texts. This modelization is close to tblard/tf-allocine based on CamemBERT model. The problem of the modelizations based on CamemBERT is at the scaling moment, for the production phase, for example. Indeed, inference cost can be a technological issue. To counteract this effect, we propose this modelization which **divides the inference time by two** with the same consumption power thanks to DistilCamemBERT. The dataset comprises 204,993 reviews for training and 4,999 reviews for the test from Amazon, and 235,516 and 4,729 critics from Allocine website. The dataset is labeled into five categories:
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗SeedVR2-GGUF
cmekaThis is a GGUF quantization of SeedVR2 using llama.cpp and a custom patch (lcpp-seedvr.patch) as described in ComfyUI-GGUF Install the official SeedVR ComfyUI node and place the model in the "models/SEEDVR2" folder. https://github.com/numz/ComfyUI-SeedVR2_VideoUpscaler?tab=readme-ov-file#-installation
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Lilith_AI_8B
CMM7590基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗acestep-5Hz-lm-4B-GGUF
cmp-nct基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗demodokos-foundry-music-v4
cmp-nct基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Input Text→ Output Audio
Price not verifiedCheck multimodal and channel pricing separately
View details ↗demodokos-foundry-tts-v4
cmp-nct基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Audio
Price not verifiedCheck multimodal and channel pricing separately
View details ↗llava-1.6-gguf
cmp-nctUpdate: PR is merged, llama.cpp now natively supports these models Important: Verify that processing a simple question with any image at least uses 1200 tokens of prompt processing, that shows that the new PR is in use. If your prompt is just 576 + a few tokens, you are using llava-1.5 code (or projector) and this is incompatible with llava-1.6 **note** Keep in mind the different fine tunes as described in the llama.cpp llava readme, it's essential to use the non defaults for non vicuna models The mmproj files are the embedded ViT's that came with llava-1.6, I've not compared them but given the previous releases from the team I'd be surprised if the ViT has not been fine tuned this time. If that's the case, using another ViT can cause issues. You need to use the mmproj of the right model but you can mix quantizations.
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3-14B-GGUF
cmp-nct基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3.5-27B-GGUF
cmp-nct基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3.5-35B-A3B-GGUF
cmp-nct基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3.5-4B-GGUF
cmp-nct基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3.5-9B-GGUF
cmp-nct基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3.6-27B-GGUF
cmp-nct基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3.6-35B-A3B-GGUF
cmp-nct基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗No matching models
Adjust provider, category or input/output filters. New models are added continuously.
COST EXPLORER
Great models. Clear costs.
Adjust monthly token usage to compare estimated API costs.
1 M = 1 million tokens · USD
Compares base text-token rates within the same channel
Compares base text-token rates within the same channel
Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.
MODEL HANDBOOK
Understand before you choose
How should API prices be compared?+
Separate input, output and cache rates, then estimate the same workload. Image, audio and video rates may use items, duration or resolution rather than tokens.
Do open weights mean free commercial use?+
Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.
Is the top-ranked model the best for me?+
Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.