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。
AIモデルを探す 22
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。
gemma-4-E4B-it-uncensored-heretic-GGUF
OS-Software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。
Hemmingway-1-Uncensored-Heretic-GGUF
OS-Software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。
Hy-MT2-30B-A3B-uncensored-heretic-GGUF
OS-Software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。
LFM2.5-24B-A2B-Uncensored-Heretic
OS-Software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
LFM2.5-24B-A2B-Uncensored-Heretic-GGUF
OS-SoftwareOnly the attention output projections of layers 18, 22 and 26 were changed; every other tensor and all metadata are those of the official files. Each file is compared with the official file of the same type, with llama.cpp. Refusals: keyword matching on the first 100 tokens of the answer (thinking closed with an empty ` ` block) for 100 Japanese harmful prompts. KL divergence: first-token KL on 100 Japanese prompts (OS-Software/harmless_alpaca_ja, test[:100]). MMLU: 0-shot next-token letter without thinking, all 14,042 questions or a spread of 3,510; HumanEval: greedy, 2,048 tokens, without thinking. The GGUFs keep the official sampling defaults (`temperature 0.1`, `top_k 50`, `repetition_penalty 1.05`), which llama.cpp applies automatically. The model still always thinks before answering, and its answers tend to be longer than the original's, so allow a generous output budget (8k tokens or more).
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
Measured on these weights quantized to Q4_K_M, against the official Q4_K_M. Refusals: keyword matching on the first 100 tokens of the reasoning (`reasoning_effort` low) for 100 Japanese harmful prompts. KL divergence: first-token KL on 100 Japanese prompts (OS-Software/harmless_alpaca_ja, test[:100]). This model has undergone substantial reduction of its safety alignment. As a result, it is more likely than standard models to generate harmful, inaccurate, biased, offensive, or otherwise inappropriate content. For research and experimentation only, including safety research, alignment studies, and red-teaming. Please avoid deploying it in public or end-user-facing services.
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。
Muse-Glimmer-30B-Uncensored-Heretic-GGUF
OS-Software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-heretic-ja-GGUF
OS-Software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
Qwen3.8-27B-Uncensored-Heretic-v2-GGUF
OS-Software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-Uncensored-Heretic-v3-GGUF
OS-SoftwareThis model has undergone substantial reduction of its safety alignment. As a result, it is more likely than standard models to generate harmful, inaccurate, biased, offensive, or otherwise inappropriate content. For research and experimentation only, including safety research, alignment studies, and red-teaming. Please avoid deploying it in public or end-user-facing services. All outputs should be treated as untrusted and independently verified before use. Users are solely responsible for:
翻訳待ち・原文を表示
Ternary-Bonsai-2-27B-Uncensored-Heretic-GGUF
OS-SoftwareA decensored version of Prism ML's Ternary-Bonsai-2-27B, with a Heretic LoRA baked into the ternary weights. The LoRA was baked into the official PQ2_0 model by adjusting ternary codes while preserving the original block scales. The update affected 34 matrices; the remaining 817 tensors were unchanged. This is an approximate merge, not an exact floating-point LoRA merge. **Use the Prism ML fork of llama.cpp.** Both formats require its ternary kernels and Hadamard activation transforms.
翻訳待ち・原文を表示
A decensored version of Prism ML's Ternary-Bonsai-2-27B, with an OT-Ridge LoRA baked into the ternary weights. It succeeds Ternary-Bonsai-2-27B-Uncensored-Heretic-GGUF (v1). - **Thinking that finishes**: responses with no final answer within 4,096 tokens (thinking on) 22% → 9%; with greedy decoding 70% → 16%. - **Smaller capability cost**: MMLU −1.63 → −0.66 points against the original model; HumanEval −1.83 → −0.61 points (not significant). Refusals: keyword matching on the 100 Japanese harmful prompts above (greedy, thinking off). KL divergence: first-token KL on 100 held-out Japanese prompts (Magpie-Tanuki train[400:500]); v1's card used another prompt set, so the two KL values are not comparable.
翻訳待ち・原文を表示
Ternary-Bonsai-27B-heretic-ja-GGUF
OS-Software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。
該当するモデルがありません
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。
モデル選びに、費用の視点も。
月間トークン数を調整してAPI費用を比較。
同一チャネルの基本テキスト料金を比較
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。
モデルを理解して選ぶ
API料金はどう比較しますか?+
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。
オープンウェイトは無料で商用利用できますか?+
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。
ランキング1位が最適ですか?+
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。