This release focuses on reducing false refusals and unnecessary policy-style preambles while retaining the native architecture and general capabilities of `Qwen/Qwen3.8-27B`. The final checkpoint preserves the official tokenizer, chat template, and configuration, the complete vision stack and multimodal projector, native Multi-Token Prediction (MTP) weights. Vision tensors remain unchanged and are verified separately. MTP tensors remain unchanged and are verified separately. “Aggressive” describes the strength of the low-overrefusal behavior. The intended response style is direct and substantive for benign, fictional, analytical, educational, authorized, privacy-respecting, or otherwise legitimate requests, including requests whose wording is sensitive or ambiguous.
Explore AI models 85001
Wan2.1-Fight-LoRA
joyfox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
gguf-components
JoyFusionAI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
Qwen-Image-2.1-MLX-4bit
JoyFusionAIQwen/Qwen-Image-2.1 quantized to 4-bit for Apple Silicon with mflux (`mflux-save -q 4`, commit `8c00dab2`). `--low-ram` releases the text encoder after prompt encoding and tiles the VAE decode. Measured on an M1 Max at 768×768: peak memory ~7 GB (vs. 33–36 GB without it), ~6.7 s/step, no visible quality change. Defaults recommended by the model authors: 40 steps, no guidance. Image sizes must be divisible by 16.
Qwen-Image-2.1-MLX-8bit
JoyFusionAIQwen/Qwen-Image-2.1 quantized to 8-bit for Apple Silicon with mflux (`mflux-save -q 8`, commit `8c00dab2`). `--low-ram` releases the text encoder after prompt encoding and tiles the VAE decode. Measured on an M1 Max at 768×768: peak memory ~10 GB (vs. 33–36 GB without it), ~6.7 s/step, no visible quality change. Defaults recommended by the model authors: 40 steps, no guidance. Image sizes must be divisible by 16.
Qwen-Image-2.1-Uncensored-LoRA
JoyFusionAI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。
DataFilter
JoyYizhu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。
Qwen3.8-27B-IQ4_XS-pure-GGUF
jpetrina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。
Qwen3.8-27B-MTP-IQ4_XS-pure-GGUF
jpetrina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。
Basic profile indexed · More details to follow
Published by request from the Pennyroyal community. This is a ModelOpt NVFP4 conversion of OrcaRouter’s uncensored Qwen3.8 Flash-Next checkpoint—the conversion I use for local agentic work with Pennyroyal/SGLang. I’ve also heard reports from several community members of it outperforming the stock model on agentic tasks, which added to the interest in sharing this working format. The original model modification is OrcaRouter’s work. My contribution here is the quantization, compatible packaging and runtime testing—not additional fine-tuning or uncensoring.
F5-Spanish
jpgallegoarThe F5-TTS model is finetuned specifically for Spanish language speech synthesis. This project aims to deliver high-quality, regionally diverse speech synthesis capabilities for Spanish speakers. This model is released under the CC0-1.0 license, which allows for free usage, modification, and distribution. - Voxpopuli Dataset, with mainly Peninsular Spain accents - Crowdsourced high-quality Spanish speech data: - Argentinian Spanish - Chilean Spanish - Colombian Spanish - Peruvian Spanish - Puerto Rican Spanish - Venezuelan Spanish - TEDx Spanish Corpus
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
XLM-RoBERTa is a scaled cross lingual sentence encoder. It is trained on 2.5T of data across 100 languages data filtered from Common Crawl. XLM-R achieves state-of-the-arts results on multiple cross lingual benchmarks.
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。
Basic profile indexed · More details to follow
Ornith-1.5-35B-A3B-EXL3-4.00bpw-24GB
JRamirez-UAB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
Ornith-1.5-9B-EXL3-16GB-12GB
JRamirez-UAB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
Qwen3.8-27B-DFlash2-W4A16
JRamirez-UAB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
Qwen3.8-27B-EXL3-3.85bpw-24GB
JRamirez-UAB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
Qwen3.8-27B-GPTQ-W4A16-embed-int4-24GB
JRamirez-UAB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。
Basic profile indexed · More details to follow
No matching models
Adjust provider, category or input/output filters. New models are added continuously.
Great models. Clear costs.
Adjust monthly token usage to compare estimated API costs.
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.
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.