From language to images, open weights to APIs. Understand capabilities and compare real costs.
Find the right engine for your next idea.
This model was converted to GGUF format from `Qwen/Qwen3-Reranker-0.6B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.
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。
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。
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
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。
1. Model Summary 2. Evaluation 3. Training 4. Limitations 5. License SmolLM3 is a 3B parameter language model designed to push the boundaries of small models. It supports 6 languages, advanced reasoning and long context. SmolLM3 is a fully open model that offers strong performance at the 3B–4B scale. The model is a decoder-only transformer using GQA and NoRope, it was pretrained on 11.2T tokens with a staged curriculum of web, code, math and reasoning data. Post-training included midtraining on 140B reasoning tokens followed by supervised fine-tuning and alignment via Anchored Preference Optimization (APO).
For more info, please refer to this PR: https://github.com/ggml-org/llama.cpp/pull/13050
For more info, please refer to this PR: https://github.com/ggml-org/llama.cpp/pull/13050
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。
For more info, please refer to this PR: https://github.com/ggml-org/llama.cpp/pull/13050
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。
Original model: https://huggingface.co/HuggingFaceTB/SmolVLM2-500M-Video-Instruct For more info, please refer to this PR: https://github.com/ggml-org/llama.cpp/pull/13050
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。
This model is ModelCloud/tinyllama-15M-stories repeated 4 times to make 4 experts. The model is used for testing, not intended to be used in production (unless your product is some kind of bedtime story teller) A LoRA adapter trained on first 100 paragraphs of shakespeare can be found inside `moe_shakespeare15M`
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。
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。
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。
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。
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。
Q8_0 GGUF of ggml-org/tinylaya-for-testing, a slice of convaiinnovations/laya for testing purposes only. The output is not meaningful. Do not use this model for anything other than testing a loader or a runtime.
Q8_0 GGUF (text model + mmproj) of a very small slice of openjev/openjev, for testing purposes only. The slice keeps the first 4 of 64 text layers and the first 2 of 27 vision blocks, and also cuts the width (hidden size 5120 -> 64, fewer attention heads, smaller FFN). About 34M parameters, most of them in the token embedding and output matrices. The output is not meaningful. Do not use this model for anything other than testing a loader or a runtime.
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。
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。
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。
Adjust provider, category or input/output filters. New models are added continuously.
Adjust monthly token usage to compare estimated API costs.
Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.
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.
Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.
Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.
