// Ai2 OLMo / Molmo · Text LLM
OLMo-2-0325-32B-Instruct: VRAM & local deployment
32.2B parameters. About 24.1 GB at 4-bit and 73.6 GB at BF16 with one 8K-token request.
released 2025-03-12licence: Commercial OKmemory figures are estimates
01Specs
| Publisher | Allen Institute for AI · allenai |
|---|---|
| Family / series | Ai2 OLMo / Molmo · OLMo-2 |
| Type | Text LLM (text-generation) |
| Parameters | 32.2B Source: counted from official safetensors weights |
| Context length | 4K tokens (4,096)max_position_embeddings in config.json |
| Architecture | 64 layers · GQA |
| Released weights | BF16 · 64.5 GBdownload |
| Licence | Apache-2.0 · Commercial OKPermissive licence (Apache-2.0 / MIT / CC-BY / OpenMDW): commercial use allowed. |
| Released | 2025-03-12 (Hugging Face repo created) |
02How much VRAM it needs (estimate)
Total = weights + 10% + 0.5GB overhead + KV cache for one request (FP16 KV). More concurrent users multiply the KV column.
| Precision | Weights | Total @ 8K | Smallest GPU | Mac |
|---|---|---|---|---|
| BF16 / FP16 (original) | 64.5 GB | 73.6 GB | RTX PRO 6000 96GB | Mac 128GB |
| FP8 / INT8 / Q8_0 | 34.3 GB | 40.3 GB | 2 × RTX 5090 (64GB) | Mac 64GB |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 19.5 GB | 24.1 GB | RTX 5090 32GB | Mac 64GB |
KV cache per request: 8K 2.1 GB
Bits per weight: BF16 16, FP8 8.5, 4-bit 4.85. “Fits” = total ≤ 90% of memory; Mac GPU can use ~2/3 of unified memory (≤36GB) or ~3/4 (larger). For MoE, all experts must be in memory, so size by total parameters. Method →
03How to run it
Only runtimes the publisher or the runtime’s official library names for this model.
- vLLM — mentioned in the official model card
- Transformers — mentioned in the official model card
- llama.cpp — official GGUF weights
04Official repositories & quantised builds
3 official repo(s) from allenai.
- OLMo-2-0325-32B-Instruct Instruct
- OLMo-2-0325-32B main
- OLMo-2-0325-32B-Instruct-GGUF Instruct/GGUF
05Other Ai2 OLMo / Molmo models
All 31 →| Model | Params | 4-bit total | Released |
|---|---|---|---|
| OLMo-2-0425-1B · same series | 1.49B | 2.6 GB | 2025-04-17 |
| OLMo-2-1124-7B · same series | 7.3B | 9.7 GB | 2024-10-29 |
| OLMo-2-1124-13B · same series | 13.7B | 16.4 GB | 2024-11-19 |
| Molmo2-ER | 4.85B | 4.9 GB | 2026-05-04 |
| MolmoWeb-4B | 4.85B | 4.9 GB | 2026-03-20 |
| MolmoPoint-8B | 8.68B | 7.5 GB | 2026-03-16 |
| Olmo-Hybrid-7B | 7.43B | 6.5 GB | 2026-01-28 |
| Molmo2-4B | 4.85B | 4.9 GB | 2025-12-14 |
| Molmo2-8B | 8.66B | 7.5 GB | 2025-12-14 |
| Molmo2-O-7B | 7.76B | 10.0 GB | 2025-12-14 |
| Olmo-3.1-32B-Instruct | 32.2B | 23.3 GB | 2025-12-10 |
06Sources
Data checked 2025-03-14. Parameters, context and licence are copied from the official repository; memory figures are our estimates.