Allen AI
OLMo 2 32B
6.5KDownloads148LikesMar 2025Veröffentlicht4K TokenKontextApache 2.0Lizenz76 StarkQualität
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.
Loslegen
— kopieren & einfügen, um lokal auszuführenCopy-paste commands to run OLMo 2 32B on your machine.
Run
lms load OLMo-2-0325-32B-Instruct && lms server startQuick 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
- •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
Verwandte Modelle
Schnellauswahl
Beste Hardware
Top-Empfehlungen für OLMo 2 32B
Dieses Modell ausführen
Quantisierungsoptionen
VRAM-Schätzungen nach Quantisierungsstufe
No hardware detected — fit column shows raw VRAM estimates
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
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
General
Chatbot Arena—
IFEval85.6%
Source: official · 2025-03-25
Hardware-Kompatibilität
Eignungsschätzungen für alle Hardware
Computing compatibility...
Speicheraufschlüsselung
Reference: RTX 2060 6GB
Weights19.5 GB
KV Cache3.9 GB
Runtime1.2 GB
Headroom0.6 GB
Häufig gestellte Fragen
FAQ — OLMo 2 32B
Siehe auch