Athene-70B-IMat-GGUF
legraphista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。
言語から画像、オープンウェイトからAPIまで。能力と実際の費用を比較。
次のアイデアに合うAIを見つけましょう。
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。
基本情報を収録・詳細は順次追加
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。
Original Model: CohereForAI/c4ai-command-r-plus-08-2024 Original dtype: `FP16` (`float16`) Quantized by: llama.cpp b3645 IMatrix dataset: here If the model file is big, it has been split into multiple files. In order to download them all to a local folder, run: According to this investigation, it appears that lower quantizations are the only ones that benefit from the imatrix input (as per hellaswag results).
翻訳待ち・原文を表示
Original Model: THUDM/codegeex4-all-9b Original dtype: `BF16` (`bfloat16`) Quantized by: https://github.com/ggerganov/llama.cpp/pull/8031 IMatrix dataset: here If the model file is big, it has been split into multiple files. In order to download them all to a local folder, run: According to this investigation, it appears that lower quantizations are the only ones that benefit from the imatrix input (as per hellaswag results).
翻訳待ち・原文を表示
_Llama.cpp imatrix quantization of mistralai/Codestral-22B-v0.1 (legraphista/Codestral-22B-v0.1-hf-FIM-fix)_ Original model: mistralai/Codestral-22B-v0.1 Quantized HF Model: legraphista/Codestral-22B-v0.1-hf-FIM-fix Original dtype: `BF16` (`bfloat16`) Quantized by: llama.cpp b3046 IMatrix dataset: here If the model file is big, it has been split into multiple files. In order to download them all to a local folder, run:
翻訳待ち・原文を表示
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: google/datagemma-rig-27b-it Original dtype: `BF16` (`bfloat16`) Quantized by: llama.cpp b3750 IMatrix dataset: here If the model file is big, it has been split into multiple files. In order to download them all to a local folder, run: According to this investigation, it appears that lower quantizations are the only ones that benefit from the imatrix input (as per hellaswag results).
翻訳待ち・原文を表示
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。
基本情報を収録・詳細は順次追加
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。
Original Model: deepseek-ai/DeepSeek-V2.5 Original dtype: `BF16` (`bfloat16`) Quantized by: llama.cpp b3675 IMatrix dataset: here If the model file is big, it has been split into multiple files. In order to download them all to a local folder, run: According to this investigation, it appears that lower quantizations are the only ones that benefit from the imatrix input (as per hellaswag results).
翻訳待ち・原文を表示
Original Model: deepseek-ai/DeepSeek-V2-Lite-Chat Original dtype: `BF16` (`bfloat16`) Quantized by: llama.cpp fork PR 7519 IMatrix dataset: here If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run: According to this investigation, it appears that lower quantizations are the only ones that benefit from the imatrix input (as per hellaswag results).
翻訳待ち・原文を表示
Original Model: deepseek-ai/DeepSeek-V2-Lite Original dtype: `BF16` (`bfloat16`) Quantized by: llama.cpp https://github.com/ggerganov/llama.cpp/pull/7519 IMatrix dataset: here If the model file is big, it has been split into multiple files. In order to download them all to a local folder, run: According to this investigation, it appears that lower quantizations are the only ones that benefit from the imatrix input (as per hellaswag results).
翻訳待ち・原文を表示
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: cognitivecomputations/dolphin-2.9.1-llama-3-8b Original dtype: `BF16` (`bfloat16`) Quantized by: llama.cpp b3006 IMatrix dataset: here If the model file is big, it has been split into multiple files. In order to download them all to a local folder, run: According to this investigation, it appears that lower quantizations are the only ones that benefit from the imatrix input (as per hellaswag results).
翻訳待ち・原文を表示
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。
基本情報を収録・詳細は順次追加
Original Model: cognitivecomputations/dolphin-2.9.2-Phi-3-Medium Original dtype: `BF16` (`bfloat16`) Quantized by: llama.cpp b3072 IMatrix dataset: here If the model file is big, it has been split into multiple files. In order to download them all to a local folder, run: According to this investigation, it appears that lower quantizations are the only ones that benefit from the imatrix input (as per hellaswag results).
翻訳待ち・原文を表示
Original Model: google/gemma-2-27b-it Original dtype: `BF16` (`bfloat16`) Quantized by: llama.cpp b3790 IMatrix dataset: here If the model file is big, it has been split into multiple files. In order to download them all to a local folder, run: According to this investigation, it appears that lower quantizations are the only ones that benefit from the imatrix input (as per hellaswag results).
翻訳待ち・原文を表示
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。
提供元・分類・入出力の条件を変更してください。新しいモデルを随時追加しています。
月間トークン数を調整してAPI費用を比較。
収集済みの比較可能な100万トークン当たり米ドル料金です。キャッシュ割引、段階料金、追加推論出力、税金は含みません。最新料金は出典で確認してください。
入力・出力・キャッシュ料金を分け、同じ用途と使用量で総費用を比較します。画像・音声・動画は枚数、時間、解像度で課金される場合があります。
必ずしもそうではありません。バージョンごとのライセンス、商用制限、ポリシーを確認してください。自前運用には計算資源と保守費用も必要です。
順位はテスト、バージョン、評価方法によります。実際の業務データで精度、遅延、安定性、費用を比較してください。