paloalma models
2 paloalma models from paloalma on Hugging Face, from 72.3B to 72.3B parameters, published by paloalma in BF16, with a 32K-token context. The smallest official model, Le_Triomphant-ECE-TW3, needs about 162 GB of VRAM at its published precision; the cheapest live fit is AMD MI300X at $2.63/hr.
Pick a size
One row per official paloalma 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 |
|---|---|---|---|---|---|---|---|
| Le_Triomphant-ECE-TW3 | 72.3B | 162 GB | 80.8 GB | 40.4 GB | AMD MI300X | $2.63/hr | 80.0 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 (2)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Le_Triomphant-ECE-TW3 | 72.3B | BF16 | 162 GB | AMD MI300X | $2.63/hr |
| TW3-JRGL-v2 | 72.3B | BF16 | 162 GB | AMD MI300X | $2.63/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.