Cognitive ComputationsCognitive Computations

Dolphin 2.9 8B

レガシー
6.3Kダウンロード493いいねApr 2024公開日33K トークンコンテキストApache 2.0ライセンス6 入門品質

Dolphin 2.9 8B (8B parameters) requires approximately 8.6 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 10 GB of VRAM.

はじめに

— コピー&ペーストでローカル実行

Copy-paste commands to run Dolphin 2.9 8B on your machine.

Run

ollama run dolphin-llama3

Quick specs

Parameters8B
Architecturedense
Context33K tokens
Modalitytext
Min RAM3.1 GB
Rec. RAM4.9 GB (Q4_K_M)
LicenseApache 2.0
FamilyDolphin
Chat

About this model

Curated and trained by Eric Hartford, Lucas Atkins, and Fernando Fernandes, and Cognitive Computations

  • learning_rate: 2e-05
  • train_batch_size: 3
  • eval_batch_size: 3
  • distributed_type: multi-GPU
  • gradient_accumulation_steps: 4

あなたのハードウェア

検出中...

おすすめ

最適なハードウェア

Dolphin 2.9 8Bのおすすめ

このモデルを実行

量子化オプション

量子化レベル別VRAM推定値

No hardware detected — fit column shows raw VRAM estimates

QuantBitsVRAMQualityFit
Q2_K
2
3.1 GB
Low
Q3_K_S
3
3.9 GB
Low
NVFP4
4
4.5 GB
Medium
Q4_K_M
4
4.9 GB
Medium
Q5_K_M
5
5.8 GB
High
Q6_K
6
6.6 GB
High
Q8_0
8
8.6 GB
Very High
F16
16
16.4 GB
Maximum

Quality benchmarks

Dolphin 2.9 8B benchmark scores

Benchmark verified

Reasoning

MMLU-Pro19.7%
GPQA Diamond4.9%
MATH-5005.7%
ARC Challenge75.0%

General

Chatbot Arena
IFEval38.5%

Source: community · 2024-04-18

ハードウェア互換性

全ハードウェアの適合度推定

カリキュレーターを開く

Computing compatibility...

メモリ内訳

Reference: RTX 2060 6GB

Weights4.9 GB
KV Cache2.0 GB
Runtime1.2 GB
Headroom0.6 GB

よくある質問

FAQ — Dolphin 2.9 8B

関連項目