Molmo models
3 Molmo models from Ai2 on Hugging Face, from 4.9B to 8.7B parameters, published by Ai2 in F32, with contexts from 4K to 36K tokens. The smallest official model, Molmo2-4B, needs about 21.7 GB of VRAM at its published precision; the cheapest live fit is RTX A5000 at $0.176/hr.
Part of the OLMo series
Pick a size
One row per official Molmo size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| Molmo2-4B | 4.9B | 21.7 GB | 5.4 GB | 2.7 GB | RTX A5000 | $0.176/hr | 4.5 GB |
| Molmo-7B-D-0924 | 8.0B | 35.9 GB | 9.0 GB | 4.5 GB | RTX A6000 | $0.363/hr | 1.8 GB |
| Molmo2-8B | 8.7B | 38.7 GB | 9.7 GB | 4.8 GB | RTX A6000 | $0.363/hr | 4.5 GB |
VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.
Official models (3)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Molmo2-4B | 4.9B | F32 | 21.7 GB | RTX A5000 | $0.176/hr |
| Molmo-7B-D-0924 | 8.0B | F32 | 35.9 GB | RTX A6000 | $0.363/hr |
| Molmo2-8B | 8.7B | F32 | 38.7 GB | RTX A6000 | $0.363/hr |
VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.