EliteReplay-BIRD-4B
hananour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
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 ↗DISCOVER & COMPARE
探索 AI 模型 84999
Qwen3.8-27B-GGUF
hanchen1145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
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗cornelius
HanClintoMobileViT-XXS corner detector trained to locate the four corners of a CCG card (Magic: The Gathering, Pokémon, etc.) in a photograph or video frame. All IoU values are quadrilateral IoU between predicted and labelled card corners. `bad` counts predictions with IoU `< 0.5`; `collapse` counts geometrically degenerate predictions where two predicted corners nearly coincide. Cornelius remains the stable, conservative default. The `fastweb-single` family is also available through the stable channel for consumers that explicitly select it; it is a smaller EfficientViT-B0 global-token SimCC detector being evaluated as a faster replacement candidate. Both models use the same 384×384 input contract and produce `corners`, compatibility `presence`, and `sharpness` outputs.
译文排队中 · 当前显示来源原文
输入 图像→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗milo
HanClintoMobileViT-XXS backbone trained with ArcFace loss (multitask: illustration_id + set_code) to produce 128-dimensional L2-normalised embeddings of CCG card images for nearest-neighbour retrieval. The easiest way to use Milo is through the CollectorVision library, which handles corner detection, dewarping, gallery loading, and nearest-neighbour search: Gallery files built with Milo v1.0.0 use `milo1` in their filename. Embeddings from different Milo versions are **not** compatible — rebuild the gallery when upgrading.
译文排队中 · 当前显示来源原文
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗qwen2.5-3b-instruct-indo-sft
handikaawork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
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 ↗Qwen3.8-27B-nvfp4-NInfer
HandleCoding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。
输入 文本 · 图像→ 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 ↗CodeRankEmbed-flash-attn
handwoven8588A **bf16 quantization of `nomic-ai/CodeRankEmbed`** with a custom `modeling_hf_nomic_bert.py`, shipped in this repo, that **picks one of three attention implementations for the hardware it runs on.** It is not a finetune — the weights are the original CodeRankEmbed weights cast to bf16 (no further training). Two of the three replace the original's padded `O(seq²)` attention with an `O(N)` unpadded path; the third keeps the original's algorithm as the correctness reference and universal fallback. `nomic-ai/CodeRankEmbed` loads through `trust_remote_code`, and its attention path is **eager only** — activation memory grows as `batch × heads × seq²`, which runs out of memory at large batches even though the model is only 137M params. This repo adds two attention paths that compute the same attention in `O(N)` memory by packing unpadded sequences, so the large batches that the eager path cannot fit run comfortably — with **parity embeddings** (no quality change): - `torch_varlen` — `torch.nn.attention.varlen.varlen_attn`, shipped in torch itself (no extra package), available from torch **2.10.0** onward. - `flash_attn` — the `flash_attn` package's varlen kernel. Kept as a fallback for older torch builds that don't yet have `torch.nn.attention.varlen` but do have `flash_attn` installed. This package is **optional**.
译文排队中 · 当前显示来源原文
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Breeze-ASR-25-gguf
handy-computerGGUF conversions of MediaTek-Research/Breeze-ASR-25 for use with transcribe.cpp. Ported from upstream commit cffe7cc, pinned 2026-06-29. Validated against the transformers reference at transcribe.cpp commit 3848875 on 2026-06-29. MediaTek Research's Breeze-ASR-25 — a fine-tune of OpenAI Whisper large-v2, converted to GGUF for transcribe.cpp. Optimized for Taiwanese Mandarin (it emits **Traditional Chinese**) and English, with explicit support for Mandarin-English code-switching (intra- and inter-sentential). Trained on ~11,749 hours: 10,000 h synthetic Mandarin (ODC Synth), 1,738 h English (CommonVoice17) and 11 h real code-switch (NTUML2021). Architecturally identical to Whisper large-v2 (encoder-decoder transformer, 30-second windows with chunked long-form decoding); it retains Whisper's 99-language tokenizer, but only Mandarin and English are optimized and validated — other languages remain technically accessible but out of scope.
译文排队中 · 当前显示来源原文
输入 音频→ 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 ↗canary-180m-flash-gguf
handy-computerGGUF conversions of nvidia/canary-180m-flash for use with transcribe.cpp. Ported from upstream commit b12ab41, pinned 2026-05-08. Validated against the NeMo reference at transcribe.cpp commit db53eda on 2026-05-08. Offline multilingual speech-to-text and translation. A multitask AED with a 17-layer FastConformer encoder and a 4-layer Transformer decoder. Supports automatic speech recognition in English, German, Spanish, and French, and bidirectional EN↔{DE, ES, FR} translation. Takes a 16 kHz mono WAV and produces a transcript. Not a streaming model; word/segment timestamps are upstream-experimental and not exposed in the v1 port.
译文排队中 · 当前显示来源原文
输入 音频→ 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 ↗canary-1b-flash-gguf
handy-computerGGUF conversions of nvidia/canary-1b-flash for use with transcribe.cpp. Ported from upstream commit a9a55e0, pinned 2026-05-08. Validated against the NeMo reference at transcribe.cpp commit db53eda on 2026-05-08. Offline multilingual speech-to-text and translation. A multitask AED with a 32-layer FastConformer encoder and a 4-layer Transformer decoder. Supports automatic speech recognition in English, German, Spanish, and French, and bidirectional EN↔{DE, ES, FR} translation. Takes a 16 kHz mono WAV and produces a transcript. Not a streaming model; word/segment timestamps are upstream-experimental and not exposed in the v1 port.
译文排队中 · 当前显示来源原文
输入 音频→ 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 ↗canary-1b-gguf
handy-computerPorted from upstream commit 1698acf, pinned 2026-05-08. Validated against the NeMo reference at transcribe.cpp commit db53eda on 2026-05-08. Offline multilingual speech-to-text and translation. A multitask AED with a 24-layer FastConformer encoder and a 24-layer Transformer decoder — the original canary release. Supports automatic speech recognition in English, German, Spanish, and French, and translation between supported pairs. Takes a 16 kHz mono WAV and produces a transcript. Not a streaming model. **License: CC-BY-NC-4.0 (non-commercial only)** — the only canary variant under a non-commercial license. WER on the full LibriSpeech test-clean split (2,620 utterances), batch size 1, timestamps none. Figures without a commit were published before provenance was recorded.
译文排队中 · 当前显示来源原文
输入 音频→ 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 ↗canary-1b-v2-gguf
handy-computerGGUF conversions of nvidia/canary-1b-v2 for use with transcribe.cpp. Ported from upstream commit 87bc526, pinned 2026-05-08. Validated against the NeMo reference at transcribe.cpp commit db53eda on 2026-05-08. Offline multilingual speech-to-text and translation across 25 European languages. A multitask AED with a 32-layer FastConformer encoder and an 8-layer Transformer decoder. Supports automatic speech recognition for any of the 25 supported languages, plus translation between supported language pairs (per the upstream model card). Takes a 16 kHz mono WAV and produces a transcript. Not a streaming model; word and segment timestamps from the upstream model are not exposed in the v1 port.
译文排队中 · 当前显示来源原文
输入 音频→ 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 ↗canary-qwen-2.5b-gguf
handy-computerGGUF conversions of nvidia/canary-qwen-2.5b for use with transcribe.cpp. Ported from upstream commit b1469e1, pinned 2026-05-15. Validated against the NeMo SALM 2.7.3 reference at transcribe.cpp commit 6f6c699 on 2026-05-16. Offline English speech-to-text. NeMo SALM (Speech-Augmented Language Model): a FastConformer audio encoder (32 layers, `d_model=1024`) feeds audio embeddings into a Qwen3-1.7B causal LM (28 layers, `hidden_size=2048`) via audio-token injection at a sentinel position in the prompt. English only. Takes a 16 kHz mono WAV and produces a transcript via greedy decoding.
译文排队中 · 当前显示来源原文
输入 音频→ 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 ↗cohere-transcribe-03-2026-gguf
handy-computerGGUF conversions of CohereLabs/cohere-transcribe-03-2026 for use with transcribe.cpp. Ported from upstream commit 76b8b23, pinned 2026-04-16. Validated against the Transformers reference at transcribe.cpp commit bf0d0b7 on 2026-04-18. Offline multilingual speech-to-text covering 14 languages (English, French, German, Spanish, Italian, Portuguese, Dutch, Polish, Greek, Arabic, Japanese, Chinese, Vietnamese, Korean). A Conformer encoder with a Transformer encoder-decoder head (cross-attention, tied token embedding). Takes a 16 kHz mono WAV and produces a transcript. Decoding is autoregressive.
译文排队中 · 当前显示来源原文
输入 音频→ 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 ↗cohere-transcribe-arabic-07-2026-gguf
handy-computerPorted from upstream commit 0a8193c, pinned 2026-07-07. Validated against the Transformers reference at transcribe.cpp commit d89ecb7 on 2026-07-07. Offline Arabic speech-to-text, including dialectal Arabic and Arabic-English code-switching, with English as a secondary language. An Arabic-focused adaptation of the Cohere Transcribe 03-2026 architecture: a Conformer encoder with a Transformer encoder-decoder head (cross-attention, tied token embedding). Takes a 16 kHz mono WAV and a language flag (`-l ar` or `-l en`) and produces a transcript. Decoding is autoregressive. WER on the full FLEURS ar split (428 utterances), batch size 8, timestamps none. Figures without a commit were published before provenance was recorded.
译文排队中 · 当前显示来源原文
输入 音频→ 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 ↗diar_streaming_sortformer_4spk-v2.1-gguf
handy-computer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。
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Fun-ASR-MLT-Nano-2512-gguf
handy-computerGGUF conversions of FunAudioLLM/Fun-ASR-MLT-Nano-2512 for use with transcribe.cpp. Ported from upstream commit cf67a93, pinned 2026-05-06. Validated against the FunASR reference at transcribe.cpp commit f094d28 on 2026-05-06. Offline speech-to-text covering 31 languages, with focused optimization on East and Southeast Asian languages: Chinese, English, Cantonese, Japanese, Korean, Vietnamese, Indonesian, Thai, Malay, Filipino, plus Arabic, Hindi, and 19 European languages (Bulgarian, Croatian, Czech, Danish, Dutch, Estonian, Finnish, Greek, Hungarian, Irish, Latvian, Lithuanian, Maltese, Polish, Portuguese, Romanian, Slovak, Slovenian, Swedish). Same architecture as Fun-ASR-Nano-2512 (~800M trainable parameters: frozen SenseVoiceEncoderSmall + 2-layer audio adaptor + bundled Qwen3-0.6B LLM); trained on a smaller multilingual corpus ("hundreds of thousands of hours" per the model card, vs Nano's "tens of millions"). Takes a 16 kHz mono WAV and emits text. Not streaming, no translation, no timestamps. ITN (inverse text normalization) is on by default, matching upstream, for readable casing, punctuation, and digits; pass `--no-itn` for spoken-form output.
译文排队中 · 当前显示来源原文
输入 音频→ 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 ↗Fun-ASR-Nano-2512-gguf
handy-computerGGUF conversions of FunAudioLLM/Fun-ASR-Nano-2512 for use with transcribe.cpp. Ported from upstream commit a7088d6, pinned 2026-05-06. Validated against the FunASR reference at transcribe.cpp commit f094d28 on 2026-05-06. Offline speech-to-text in Chinese, English, and Japanese, plus 7 Chinese dialects (Wu, Cantonese, Min, Hakka, Gan, Xiang, Jin) and 26 regional Mandarin accents. ~800M trainable parameters wrapping a frozen SenseVoiceEncoderSmall (50 SAN-M main blocks + 20 transformer blocks), a 2-layer audio adaptor (512 → 1024), and a bundled Qwen3-0.6B LLM (28 layers, 16/8 GQA, BF16) that produces the transcript autoregressively. Takes a 16 kHz mono WAV and emits text. Not a streaming model, no translation, no built-in long-form chunking, no timestamps. ITN (inverse text normalization) is off by default, since with it on English can come back all caps; pass `--itn` for digits and punctuation, which helps Chinese.
译文排队中 · 当前显示来源原文
输入 音频→ 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 ↗gigaam-v3-ctc-gguf
handy-computerPorted from upstream commit 15ef3b5, pinned 2026-05-12. Validated against the gigaam author package reference at transcribe.cpp commit 0fff13f8 on 2026-10-15. Offline Russian speech-to-text with greedy CTC decoding. 16-layer Conformer encoder with a 1×1 Conv1d CTC head. Output is lowercased Russian, no punctuation; 33-entry character vocabulary. WER on the full FLEURS ru split (775 utterances), batch sizes 1 and 8, timestamps none. Figures without a commit were published before provenance was recorded.
译文排队中 · 当前显示来源原文
输入 音频→ 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 ↗gigaam-v3-e2e-ctc-gguf
handy-computerGGUF conversions of ai-sage/GigaAM-v3 for use with transcribe.cpp. Ported from upstream commit cec030b, pinned 2026-05-12. Validated against the gigaam author package reference at transcribe.cpp commit 0fff13f8 on 2026-10-15. Offline Russian speech-to-text with greedy CTC decoding. 16-layer Conformer encoder with a 1×1 Conv1d CTC head. Output is cased Russian with punctuation, decoded from a 256-piece SentencePiece tokenizer.
译文排队中 · 当前显示来源原文
输入 音频→ 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 ↗gigaam-v3-e2e-rnnt-gguf
handy-computerGGUF conversions of ai-sage/GigaAM-v3 for use with transcribe.cpp. Ported from upstream commit ec1dc1f, pinned 2026-05-12. Validated against the gigaam author package reference at transcribe.cpp commit 0fff13f8 on 2026-10-15. Offline Russian speech-to-text with greedy RNN-T decoding. 16-layer Conformer encoder paired with an RNN-T transducer head. Output is cased Russian with punctuation, decoded from a 1024-piece SentencePiece tokenizer. Not a streaming model and does not translate. Audio past the 25 s training window is encoded in overlapping windows.
译文排队中 · 当前显示来源原文
输入 音频→ 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 ↗gigaam-v3-rnnt-gguf
handy-computerGGUF conversions of ai-sage/GigaAM-v3 for use with transcribe.cpp. Ported from upstream commit c7f128b, pinned 2026-05-12. Validated against the gigaam author package reference at transcribe.cpp commit 0fff13f8 on 2026-10-15. Offline Russian speech-to-text with greedy RNN-T decoding. Same 16-layer Conformer encoder as the e2e variant, fine-tuned to emit lowercased Russian with no punctuation; 33-entry character vocabulary.
译文排队中 · 当前显示来源原文
输入 音频→ 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 ↗granite-4.0-1b-speech-gguf
handy-computerPorted from upstream commit bd87ab8, pinned 2026-05-17. Validated against the Transformers reference at transcribe.cpp commit 275332d on 2026-05-17. Offline multilingual speech-to-text. IBM Granite Speech 4.0-1b is an audio-LLM: a Conformer encoder with block-local Shaw attention, a BLIP-2 Q-Former projector, and the Granite-4.0-1b-base LLM as an autoregressive decoder. Takes a 16 kHz mono WAV and produces a transcript; the LLM half is what writes the text. Transcribes English, French, German, Spanish, Portuguese, and Japanese. Translates between English and each of those five other languages in either direction (en ↔ fr, en ↔ de, en ↔ es, en ↔ pt, en ↔ ja) — always via English, no direct fr↔de etc. WER on the full LibriSpeech test-clean split (2,620 utterances), batch size 1, timestamps none. Figures without a commit were published before provenance was recorded.
译文排队中 · 当前显示来源原文
输入 音频→ 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 ↗granite-speech-4.1-2b-gguf
handy-computerGGUF conversions of ibm-granite/granite-speech-4.1-2b for use with transcribe.cpp. Ported from upstream commit 8f4bb5f, pinned 2026-05-17. Validated against the Transformers reference at transcribe.cpp commit 275332d on 2026-05-17. Offline multilingual speech-to-text. IBM Granite Speech 4.1-2b is an audio-LLM with the same architecture as 4.0-1b (Conformer encoder with block-local Shaw attention, BLIP-2 Q-Former projector, Granite-4.0-1b-base autoregressive LLM decoder) and improved punctuation and casing over 4.0-1b. Takes a 16 kHz mono WAV and produces a transcript. Transcribes English, French, German, Spanish, Portuguese, and Japanese. Translates between English and each of those five other languages in either direction (en ↔ fr, en ↔ de, en ↔ es, en ↔ pt, en ↔ ja) — always via English, no direct fr↔de etc.
译文排队中 · 当前显示来源原文
输入 音频→ 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 ↗暂未找到匹配模型
可以调整厂商、分类或输入输出条件；新模型正持续收录。
COST EXPLORER
好模型，也要算好成本。
调整月度 Token 用量，直观比较不同模型的预估 API 开支。
1 M = 100 万 Token · 美元计价
仅比较同一渠道的基础文本 Token 报价
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
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。