**Built From Fish Audio.** This is a fine-tuned and quantized derivative of Fish Audio Drama 3. Fish Audio does not sponsor or endorse it. Drama 3 follows an acting direction at the start of a line, but it mostly ignores one placed in the middle: `[calm] It's fine, really. [voice breaking] I just miss her.` tends to stay calm, or to go silent at the second direction. drama3-expressive-medium was fine-tuned to change delivery where the direction says. It also speaks the whole line and ends cleanly far more often. It keeps all 256 experts and runs in 24 GB of VRAM. No reference audio: each sample's seed makes up its own voice, speaking the line's language (`--task tts` with no `voice_ref`). The first table keeps the words fixed and changes only the opening direction; the second changes the delivery mid-line.

译文排队中 · 当前显示来源原文

语音合成

输入文本→ 输出音频

价格待核验多模态与渠道费用须分别核对

查看详情 ↗

加入对比来源 / 文档 ↗

drama3-small-GGUF

pentacoxian-dev

**Built with Fish Audio.** This is a compressed derivative of Fish Audio Drama 3. Fish Audio does not sponsor or endorse it. drama3-small keeps Drama 3's expressive Japanese and English voice cloning: inline tags, English style directions and director's notes. It should fit in 12 GB of VRAM. The 35B-A3B mixture-of-experts backbone was pruned to 45% of its expert slots and quantized to about 3 bits. It was then distilled back towards the original on Japanese and English speech. All samples come from this GGUF in one take, cloned from a 29-second Japanese reference recording of the repo owner's voice (used with consent).

译文排队中 · 当前显示来源原文

语音合成

输入文本→ 输出音频

价格待核验多模态与渠道费用须分别核对

查看详情 ↗

加入对比来源 / 文档 ↗

iris-3b-turbo-lora

pentacoxian-dev

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。

基础资料已收录 · 缺失资料后续补充

图像生成

输入文本→ 输出图像

价格待核验多模态与渠道费用须分别核对

查看详情 ↗

加入对比来源 / 文档 ↗

Qwen3.8-Flash-Next-IQ3E-Q8D-MTP-GGUF

pentacoxian-dev

This is a single-file GGUF of Qwen/Qwen3.8-Flash-Next with the model's multi-token-prediction (MTP) head added back in. The mix of quantizations is chosen so that every routed expert fits in 2× 32 GB of VRAM, and the MTP head lets llama.cpp decode speculatively. This model and patch is specifically tuned for dual Nvidia Tesla V100(32GB VRAM). > **This file needs a patched llama.cpp.** It uses the `qwen4exp` architecture with > MTP (`nextn`) tensors. Stock llama.cpp, Ollama and LM Studio cannot load it. See > Runtime. - unsloth GGUF revision `c8b5954a88c2775c546b92593eda40ea041d3176`. - Qwen checkpoint revision `de4b8e4d43b917e7706784d8bb445c9af86a3540`. Only the `mtp.*` tensors are taken from it.

译文排队中 · 当前显示来源原文

文本生成

输入文本→ 输出文本

价格待核验多模态与渠道费用须分别核对

查看详情 ↗

加入对比来源 / 文档 ↗

COST EXPLORER

好模型，也要算好成本。

费用分析

调整月度 Token 用量，直观比较不同模型的预估 API 开支。

每月输入 Token 10 M每月输出 Token 2 M1 M = 100 万 Token · 美元计价
仅比较同一渠道的基础文本 Token 报价

使用已采集且单位可比的 USD / 百万 Token 渠道报价。报价为采集时快照；不计缓存优惠、阶梯价、推理额外输出与税费，请以来源的当前报价为准。

MODEL HANDBOOK

读懂模型，再做选择

选型与常见问题

API 价格应该怎么比较？+

先区分输入、输出和缓存价格，再使用同一任务和用量估算总费用。图像、音频和视频可能按张、时长或分辨率计费，不能直接与 Token 单价比较。

开放权重，就代表可以免费商用吗？+

不一定。必须逐一核对具体模型版本的许可证、商用限制及使用政策。自己部署还需要考虑显存、推理资源和运维费用。

排行榜第一，就是最适合我的模型吗？+

榜单取决于测试任务、版本与评测方法。建议用实际业务样本比较准确性、时延、稳定性和成本，再选择模型。

找到适合你的 AI 模型。

探索 AI 模型 5

DeepSeek-V4.1-1017-Ablitrated-Efficient

drama3-expressive-medium-GGUF

drama3-small-GGUF

iris-3b-turbo-lora

Qwen3.8-Flash-Next-IQ3E-Q8D-MTP-GGUF

暂未找到匹配模型

好模型，也要算好成本。

读懂模型，再做选择

资讯看趋势，工具提效率，模型筑可能。