Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety. **Variations** Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants. **Model Architecture** Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.

翻訳待ち・原文を表示

テキスト生成

入力テキスト→ 出力テキスト

料金未確認マルチモーダル・チャネル料金は個別に確認

詳細を見る ↗

比較に追加出典・文書 ↗

Meta-Llama-3-8B-Instruct-GGUF

ThomasBaruzier

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。

テキスト生成

入力テキスト→ 出力テキスト

料金未確認マルチモーダル・チャネル料金は個別に確認

詳細を見る ↗

比較に追加出典・文書 ↗

Qwen2.5-0.5B-Instruct-GGUF

ThomasBaruzier

Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2: **This repo contains the instruction-tuned 0.5B Qwen2.5 model**, which has the following features: - Type: Causal Language Models - Training Stage: Pretraining & Post-training - Architecture: transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias and tied word embeddings - Number of Parameters: 0.49B - Number of Paramaters (Non-Embedding): 0.36B - Number of Layers: 24 - Number of Attention Heads (GQA): 14 for Q and 2 for KV - Context Length: Full 32,768 tokens and generation 8192 tokens The code of Qwen2.5 has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`.

翻訳待ち・原文を表示

テキスト生成

入力テキスト→ 出力テキスト

料金未確認マルチモーダル・チャネル料金は個別に確認

詳細を見る ↗

比較に追加出典・文書 ↗

Qwen2.5-1.5B-Instruct-GGUF

ThomasBaruzier

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。

テキスト生成

入力テキスト→ 出力テキスト

料金未確認マルチモーダル・チャネル料金は個別に確認

詳細を見る ↗

比較に追加出典・文書 ↗

Qwen2.5-14B-Instruct-GGUF

ThomasBaruzier

Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2: **This repo contains the instruction-tuned 14B Qwen2.5 model**, which has the following features: - Type: Causal Language Models - Training Stage: Pretraining & Post-training - Architecture: transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias - Number of Parameters: 14.7B - Number of Paramaters (Non-Embedding): 13.1B - Number of Layers: 48 - Number of Attention Heads (GQA): 40 for Q and 8 for KV - Context Length: Full 131,072 tokens and generation 8192 tokens - Please refer to this section for detailed instructions on how to deploy Qwen2.5 for handling long texts. The code of Qwen2.5 has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`.

翻訳待ち・原文を表示

テキスト生成

入力テキスト→ 出力テキスト

料金未確認マルチモーダル・チャネル料金は個別に確認

詳細を見る ↗

比較に追加出典・文書 ↗

Qwen2.5-32B-Instruct-GGUF

ThomasBaruzier

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。

テキスト生成

入力テキスト→ 出力テキスト

料金未確認マルチモーダル・チャネル料金は個別に確認

詳細を見る ↗

比較に追加出典・文書 ↗

Qwen2.5-3B-Instruct-GGUF

ThomasBaruzier

Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2: **This repo contains the instruction-tuned 3B Qwen2.5 model**, which has the following features: - Type: Causal Language Models - Training Stage: Pretraining & Post-training - Architecture: transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias and tied word embeddings - Number of Parameters: 3.09B - Number of Paramaters (Non-Embedding): 2.77B - Number of Layers: 36 - Number of Attention Heads (GQA): 16 for Q and 2 for KV - Context Length: Full 32,768 tokens and generation 8192 tokens The code of Qwen2.5 has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`.

翻訳待ち・原文を表示

テキスト生成

入力テキスト→ 出力テキスト

料金未確認マルチモーダル・チャネル料金は個別に確認

詳細を見る ↗

比較に追加出典・文書 ↗

Qwen2.5-72B-Instruct-GGUF

ThomasBaruzier

Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2: **This repo contains the instruction-tuned 72B Qwen2.5 model**, which has the following features: - Type: Causal Language Models - Training Stage: Pretraining & Post-training - Architecture: transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias - Number of Parameters: 72.7B - Number of Paramaters (Non-Embedding): 70.0B - Number of Layers: 80 - Number of Attention Heads (GQA): 64 for Q and 8 for KV - Context Length: Full 131,072 tokens and generation 8192 tokens - Please refer to this section for detailed instructions on how to deploy Qwen2.5 for handling long texts. The code of Qwen2.5 has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`.

翻訳待ち・原文を表示

テキスト生成

入力テキスト→ 出力テキスト

料金未確認マルチモーダル・チャネル料金は個別に確認

詳細を見る ↗

比較に追加出典・文書 ↗

COST EXPLORER

モデル選びに、費用の視点も。

コスト分析

月間トークン数を調整してAPI費用を比較。

月間入力トークン 10 M月間出力トークン 2 M1 M = 100万トークン・米ドル
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。

MODEL HANDBOOK

モデルを理解して選ぶ

選び方とよくある質問

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。

あなたに合う AIモデルを。

AIモデルを探す 31

DeepScaleR-1.5B-Preview-abliterated-GGUF

DeepScaleR-1.5B-Preview-GGUF

DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF

DeepSeek-R1-ReDistill-Qwen-7B-v1.1-GGUF

EXAONE-3.0-7.8B-Instruct-GGUF

EXAONE-3.5-2.4B-Instruct-GGUF

EXAONE-3.5-7.8B-Instruct-GGUF

gemma-2-27b-it-GGUF

gemma-2-2b-it-GGUF

Llama-3.1-Minitron-4B-Width-Base-GGUF

Llama-3.2-1B-Instruct-GGUF

Llama-3.2-3B-Instruct-GGUF

Llama-3.3-70B-Instruct-GGUF

Meta-Llama-3.1-405B-Instruct-GGUF

Meta-Llama-3.1-70B-Instruct-GGUF

Meta-Llama-3.1-8B-Instruct-GGUF

Meta-Llama-3-70B-Instruct-GGUF

Meta-Llama-3-8B-Instruct-GGUF

Qwen2.5-0.5B-Instruct-GGUF

Qwen2.5-1.5B-Instruct-GGUF

Qwen2.5-14B-Instruct-GGUF

Qwen2.5-32B-Instruct-GGUF

Qwen2.5-3B-Instruct-GGUF

Qwen2.5-72B-Instruct-GGUF

該当するモデルがありません

モデル選びに、費用の視点も。

モデルを理解して選ぶ

ニュースで知り、ツールで効率化、モデルで可能性を。