Edge0:ローカル推論速度(tok/s)、出典付き
2026-11-14 時点で、このデータセットには Edge0 のレシピが 10 件あります。投稿者自身の実測はまだありません。以下は公式・主張・伝聞として読んでください。日付のあるエントリは 10 件(2026-09-08〜2026-11-12)。
| モデル | エンジン | ハードウェア | tok/s | 指標 | 出典レベル | 日付 | 出典 |
|---|---|---|---|---|---|---|---|
| Edge0-120B | edge0 | 1× RTX 5090 D 24GB | 130.2 | Official Edge0 model card speed table. Headline is Q3_K chat decode 130.2; agent decode 144.6 is separate. The NVFP4 build on the same machine: chat 124.9 / agent 135.5 (https://huggingface.co/Edge0/Edge0-120B-NVFP4), note only. With the same card capped to 16GiB VRAM + 20GiB RAM (--vram-reserve-mib 8192, cgroup 20G), Q3_K gives chat 62.4 / agent 73.3 and NVFP4 chat 51.3 (a simulated budget, no separate row). The shipped model.json sets --max-context 131072, --spec 4 (MTP) and --kv int8. The card does not state the engine version or the concurrency. Official figures, no per-run raw data. | 公式 | 2026-11-12 | リンク |
| Edge0-145B | edge0 | 1× RTX 5090 D 24GB | 99.7 | Official Edge0 model card speed table. Headline is Q3_K chat decode 99.7; agent decode 121.2 is separate. The NVFP4 build on the same machine: chat 79.6 / agent 98.3 (https://huggingface.co/Edge0/Edge0-145B-NVFP4), note only. With the same card capped to 16GiB VRAM + 20GiB RAM (--vram-reserve-mib 8192, cgroup 20G), Q3_K gives chat 36.8 / agent 44.9 (a simulated budget, no separate row). The shipped model.json sets --max-context 131072, --spec 4 (MTP) and --kv int8. The card does not state the engine version or the concurrency. Official figures, no per-run raw data. | 公式 | 2026-11-12 | リンク |
| Edge0-120B | edge0 | 1× RTX 4090 24GB | 95 | Official Edge0 model card speed table. Headline is Q3_K chat decode 95.0; agent decode 104.9 is separate. The shipped model.json sets --max-context 131072, --spec 4 (MTP) and --kv int8. The card does not state the engine version or the concurrency. Official figures, no per-run raw data. | 公式 | 2026-11-12 | リンク |
| Edge0-145B | edge0 | 1× RTX 4090 24GB | 69.9 | Official Edge0 model card speed table. Headline is Q3_K chat decode 69.9; agent decode 91.7 is separate. The shipped model.json sets --max-context 131072, --spec 4 (MTP) and --kv int8. The card does not state the engine version or the concurrency. Official figures, no per-run raw data. | 公式 | 2026-11-12 | リンク |
| Edge0-145B | edge0 | Apple M2 Ultra (Metal) | 60.9 | Official Edge0 model card speed table. Headline is Q3_K chat decode 60.9; agent decode 57.0 is separate. The shipped model.json sets --max-context 131072, --spec 4 (MTP) and --kv int8. The card does not state the engine version or the concurrency. Official figures, no per-run raw data. The card says the M2 Ultra values use Metal and do not mean a macOS release is available. | 公式 | 2026-11-12 | リンク |
| Edge0-120B | edge0 | Apple M2 Ultra (Metal) | 60.4 | Official Edge0 model card speed table. Headline is Q3_K chat decode 60.4; agent decode 63.0 is separate. The shipped model.json sets --max-context 131072, --spec 4 (MTP) and --kv int8. The card does not state the engine version or the concurrency. Official figures, no per-run raw data. The card says the M2 Ultra values use Metal and do not mean a macOS release is available. | 公式 | 2026-11-12 | リンク |
| Edge0-120B | edge0 | RTX Spark N1X 60GiB | 47.2 | Official Edge0 model card speed table. Headline is Q3_K chat decode 47.2; agent decode 68.4 is separate. The NVFP4 build on the same machine: chat 45.1 / agent 68.9 (https://huggingface.co/Edge0/Edge0-120B-NVFP4), note only. The shipped model.json sets --max-context 131072, --spec 4 (MTP) and --kv int8. The card does not state the engine version or the concurrency. Official figures, no per-run raw data. | 公式 | 2026-11-12 | リンク |
| Edge0-145B | edge0 | RTX Spark N1X 60GiB | 37.7 | Official Edge0 model card speed table. Headline is Q3_K chat decode 37.7; agent decode 36.7 is separate. The NVFP4 build on the same machine: chat 40.1 / agent 46.0 (https://huggingface.co/Edge0/Edge0-145B-NVFP4), note only. The shipped model.json sets --max-context 131072, --spec 4 (MTP) and --kv int8. The card does not state the engine version or the concurrency. Official figures, no per-run raw data. | 公式 | 2026-11-12 | リンク |
| Edge0-8B-A1B-preview | edge0 | Mac mini M4 Pro 24GB | 23.9 | 23.9 tok/s decode; 1428 tok/s prefill | 主張 | 2026-09-08 | リンク |
| Edge0-35B-A3B-preview | edge0 | Mac mini M4 Pro 24GB | 14.9 | 14.9 tok/s decode; 140 tok/s prefill | 主張 | 2026-09-08 | リンク |
数値は各出典のものです。本プロジェクトでは再計測していません。行ごとにモデルと設定が異なります。出典レベル:公式 = プロジェクトまたはベンダー、実測 = 投稿者が実行(エンジンまたはレシピの作者は生データと再現手順も公開する)、伝聞 = 二次情報、主張 = 予測または再現手順なし。