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。
*👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*. **Model creator:** google **Original model**: gemma-3n-E4B-it **GGUF quantization:** provided by LM Studio team using `llama.cpp` 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible.
翻訳待ち・原文を表示
*👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*. **Model creator**: google **Original model**: gemma-4-12B-it **GGUF quantization**: provided by LM Studio team using `llama.cpp` release b10069 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible.
翻訳待ち・原文を表示
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: google **Original model**: gemma-4-12B-it **MLX quantization**: provided by LM Studio team using mlx_vlm 4-bit quantized version of gemma-4-12B-it using MLX, optimized for Apple Silicon.
翻訳待ち・原文を表示
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: google **Original model**: gemma-4-12B-it **MLX quantization**: provided by LM Studio team using mlx_vlm 5-bit quantized version of gemma-4-12B-it using MLX, optimized for Apple Silicon.
翻訳待ち・原文を表示
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: google **Original model**: gemma-4-12B-it **MLX quantization**: provided by LM Studio team using mlx_vlm 6-bit quantized version of gemma-4-12B-it using MLX, optimized for Apple Silicon.
翻訳待ち・原文を表示
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: google **Original model**: gemma-4-12B-it **MLX quantization**: provided by LM Studio team using mlx_vlm 8-bit quantized version of gemma-4-12B-it using MLX, optimized for Apple Silicon.
翻訳待ち・原文を表示
*👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*. **Model creator**: google **Original model**: gemma-4-12B-it-qat-q4_0-unquantized **GGUF quantization**: provided by LM Studio team using `llama.cpp` release b10069 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible.
翻訳待ち・原文を表示
*👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*. **Model creator**: google **Original model**: gemma-4-26B-A4B-it **GGUF quantization**: provided by LM Studio team using `llama.cpp` release b10069 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible.
翻訳待ち・原文を表示
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: google **Original model**: gemma-4-26B-A4B-it **MLX quantization**: provided by LM Studio team using mlx_vlm 4-bit quantized version of gemma-4-26B-A4B-it using MLX, optimized for Apple Silicon.
翻訳待ち・原文を表示
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: google **Original model**: gemma-4-26B-A4B-it **MLX quantization**: provided by LM Studio team using mlx_vlm 5-bit quantized version of gemma-4-26B-A4B-it using MLX, optimized for Apple Silicon.
翻訳待ち・原文を表示
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: google **Original model**: gemma-4-26B-A4B-it **MLX quantization**: provided by LM Studio team using mlx_vlm 6-bit quantized version of gemma-4-26B-A4B-it using MLX, optimized for Apple Silicon.
翻訳待ち・原文を表示
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: google **Original model**: gemma-4-26B-A4B-it **MLX quantization**: provided by LM Studio team using mlx_vlm 8-bit quantized version of gemma-4-26B-A4B-it using MLX, optimized for Apple Silicon.
翻訳待ち・原文を表示
*👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*. **Model creator**: google **Original model**: gemma-4-26B-A4B-it-qat-q4_0-unquantized **GGUF quantization**: provided by LM Studio team using `llama.cpp` release b10069 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible.
翻訳待ち・原文を表示
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: google **Original model**: gemma-4-26B-A4B-it-QAT **MLX quantization**: provided by LM Studio team using mlx_vlm 4-bit quantized version of gemma-4-26B-A4B-it-QAT using MLX, optimized for Apple Silicon.
翻訳待ち・原文を表示
*👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*. **Model creator**: google **Original model**: gemma-4-31B-it **GGUF quantization**: provided by LM Studio team using `llama.cpp` release b10069 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible.
翻訳待ち・原文を表示
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: google **Original model**: gemma-4-31B-it **MLX quantization**: provided by LM Studio team using mlx_vlm 4-bit quantized version of gemma-4-31B-it using MLX, optimized for Apple Silicon.
翻訳待ち・原文を表示
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: google **Original model**: gemma-4-31B-it **MLX quantization**: provided by LM Studio team using mlx_vlm 5-bit quantized version of gemma-4-31B-it using MLX, optimized for Apple Silicon.
翻訳待ち・原文を表示
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: google **Original model**: gemma-4-31B-it **MLX quantization**: provided by LM Studio team using mlx_vlm 6-bit quantized version of gemma-4-31B-it using MLX, optimized for Apple Silicon.
翻訳待ち・原文を表示
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: google **Original model**: gemma-4-31B-it **MLX quantization**: provided by LM Studio team using mlx_vlm 8-bit quantized version of gemma-4-31B-it using MLX, optimized for Apple Silicon.
翻訳待ち・原文を表示
*👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*. **Model creator**: google **Original model**: gemma-4-31B-it-qat-q4_0-unquantized **GGUF quantization**: provided by LM Studio team using `llama.cpp` release b10069 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible.
翻訳待ち・原文を表示
*👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*. **Model creator**: google **Original model**: gemma-4-E2B-it **GGUF quantization**: provided by LM Studio team using `llama.cpp` release b10076 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible.
翻訳待ち・原文を表示
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: google **Original model**: gemma-4-E2B-it **MLX quantization**: provided by LM Studio team using mlx_vlm 4-bit quantized version of gemma-4-E2B-it using MLX, optimized for Apple Silicon.
翻訳待ち・原文を表示
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: google **Original model**: gemma-4-E2B-it **MLX quantization**: provided by LM Studio team using mlx_vlm 5-bit quantized version of gemma-4-E2B-it using MLX, optimized for Apple Silicon.
翻訳待ち・原文を表示
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: google **Original model**: gemma-4-E2B-it **MLX quantization**: provided by LM Studio team using mlx_vlm 6-bit quantized version of gemma-4-E2B-it using MLX, optimized for Apple Silicon.
翻訳待ち・原文を表示
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。
