Allen AIAllen AI

OLMo 2 32B

6.5Kダウンロード148いいねMar 2025公開日4K トークンコンテキストApache 2.0ライセンス76 優秀品質

OLMo 2 32B (32B parameters) requires approximately 25.2 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 29 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 OLMo 2 32B on your machine.

Run

lms load OLMo-2-0325-32B-Instruct && lms server start

Quick specs

Parameters32B
Architecturedense
Context4K tokens
Modalitytext
Min RAM12.5 GB
Rec. RAM19.5 GB (Q4_K_M)
LicenseApache 2.0
FamilyOLMo
Chat

About this model

OLMo 2 32B is Allen AI's fully open 32B-parameter language model, the largest in the OLMo 2 family. Trained on 6T tokens from the Dolma dataset, post-trained with Tülu 3 SFT, DPO, and RLVR. First fully open model to outperform GPT-3.5 and GPT-4o mini on academic benchmarks.

  • First fully open model to outperform GPT-3.5 and GPT-4o mini
  • Fully open: weights, data, code, and training recipes
  • Post-trained with SFT, DPO, and Reinforcement Learning from Verifiable Rewards
  • Trained on 6T tokens from the Dolma dataset

関連モデル

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

OLMo 2 32B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
12.5 GB
Low
Q3_K_S
3
15.7 GB
Low
NVFP4
4
17.9 GB
Medium
Q4_K_M
4
19.5 GB
Medium
Q5_K_M
5
23.0 GB
High
Q6_K
6
26.2 GB
High
Q8_0
8
34.2 GB
Very High
F16
16
65.6 GB
Maximum

Quality benchmarks

OLMo 2 32B benchmark scores

Benchmark verified

General

Chatbot Arena
IFEval85.6%

Source: official · 2025-03-25

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

Weights19.5 GB
KV Cache3.9 GB
Runtime1.2 GB
Headroom0.6 GB

よくある質問

FAQ — OLMo 2 32B

関連項目